🧠

Artificial Intelligence

Explore the latest in machine learning, deep learning, natural language processing, and AI applications

7597
Total Items
5221
Papers
372
Videos
41
Books
1635
Blogs
208
News
46
Podcasts
50
GitHub
2
Q&A
Browsing by date

Navigate through content by publication date

Fri, Apr 3

33 items found

1 of 190
📄 paper

AstroConcepts: A Large-Scale Multi-Label Classification Corpus for Astrophysics

Scientific multi-label text classification suffers from extreme class imbalance, where specialized terminology exhibits severe power-law distributions that challenge standard classification approaches. Existing scientific corpora lack comprehensive controlled vocabularies, focusing instead on broad categories and limiting systematic study of extreme imbalance. We introduce AstroConcepts, a corpus of English abstracts from 21,702 published astrophysics papers, labeled with 2,367 concepts from the Unified Astronomy Thesaurus. The corpus exhibits severe label imbalance, with 76% of concepts having fewer than 50 training examples. By releasing this resource, we enable systematic study of extreme class imbalance in scientific domains and establish strong baselines across traditional, neural, and vocabulary-constrained LLM methods. Our evaluation reveals three key patterns that provide new insights into scientific text classification. First, vocabulary-constrained LLMs achieve competitive performance relative to domain-adapted models in astrophysics classification, suggesting a potential for parameter-efficient approaches. Second, domain adaptation yields relatively larger improvements for rare, specialized terminology, although absolute performance remains limited across all methods. Third, we propose frequency-stratified evaluation to reveal performance patterns that are hidden by aggregate scores, thereby making robustness assessment central to scientific multi-label evaluation. These results offer actionable insights for scientific NLP and establish benchmarks for research on extreme imbalance.

AI advanced Natural Language ProcessingMachine Learning
By: Atilla Kaan Alkan, Felix Grezes, Sergi Blanco-Cuaresma +5 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

Adam's Law: Textual Frequency Law on Large Language Models

While textual frequency has been validated as relevant to human cognition in reading speed, its relatedness to Large Language Models (LLMs) is seldom studied. We propose a novel research direction in terms of textual data frequency, which is an understudied topic, to the best of our knowledge. Our framework is composed of three units. First, this paper proposes Textual Frequency Law (TFL), which indicates that frequent textual data should be preferred for LLMs for both prompting and fine-tuning. Since many LLMs are closed-source in their training data, we propose using online resources to estimate the sentence-level frequency. We then utilize an input paraphraser to paraphrase the input into a more frequent textual expression. Next, we propose Textual Frequency Distillation (TFD) by querying LLMs to conduct story completion by further extending the sentences in the datasets, and the resulting corpora are used to adjust the initial estimation. Finally, we propose Curriculum Textual Frequency Training (CTFT) that fine-tunes LLMs in an increasing order of sentence-level frequency. Experiments are conducted on our curated dataset Textual Frequency Paired Dataset (TFPD) on math reasoning, machine translation, commonsense reasoning and agentic tool calling. Results show the effectiveness of our framework.

AI advanced Natural Language Processing
By: Hongyuan Adam Lu, Z. L., Victor Wei +5 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

The Expert Strikes Back: Interpreting Mixture-of-Experts Language Models at Expert Level

Mixture-of-Experts (MoE) architectures have become the dominant choice for scaling Large Language Models (LLMs), activating only a subset of parameters per token. While MoE architectures are primarily adopted for computational efficiency, it remains an open question whether their sparsity makes them inherently easier to interpret than dense feed-forward networks (FFNs). We compare MoE experts and dense FFNs using $k$-sparse probing and find that expert neurons are consistently less polysemantic, with the gap widening as routing becomes sparser. This suggests that sparsity pressures both individual neurons and entire experts toward monosemanticity. Leveraging this finding, we zoom out from the neuron to the expert level as a more effective unit of analysis. We validate this approach by automatically interpreting hundreds of experts. This analysis allows us to resolve the debate on specialization: experts are neither broad domain specialists (e.g., biology) nor simple token-level processors. Instead, they function as fine-grained task experts, specializing in linguistic operations or semantic tasks (e.g., closing brackets in LaTeX). Our findings suggest that MoEs are inherently interpretable at the expert level, providing a clearer path toward large-scale model interpretability. Code is available at: https://github.com/jerryy33/MoE_analysis

AI advanced Natural Language ProcessingArtificial Intelligence
By: Jeremy Herbst, Jae Hee Lee, Stefan Wermter
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

Neuro-RIT: Neuron-Guided Instruction Tuning for Robust Retrieval-Augmented Language Model

Retrieval-Augmented Language Models (RALMs) have demonstrated significant potential in knowledge-intensive tasks; however, they remain vulnerable to performance degradation when presented with irrelevant or noisy retrieved contexts. Existing approaches to enhance robustness typically operate via coarse-grained parameter updates at the layer or module level, often overlooking the inherent neuron-level sparsity of Large Language Models (LLMs). To address this limitation, we propose Neuro-RIT (Neuron-guided Robust Instruction Tuning), a novel framework that shifts the paradigm from dense adaptation to precision-driven neuron alignment. Our method explicitly disentangles neurons that are responsible for processing relevant versus irrelevant contexts using attribution-based neuron mining. Subsequently, we introduce a two-stage instruction tuning strategy that enforces a dual capability for noise robustness: achieving direct noise suppression by functionally deactivating neurons exclusive to irrelevant contexts, while simultaneously optimizing targeted layers for evidence distillation. Extensive experiments across diverse QA benchmarks demonstrate that Neuro-RIT consistently outperforms strong baselines and robustness-enhancing methods.

AI advanced Natural Language ProcessingArtificial Intelligence
By: Jaemin Kim, Jae O Lee, Sumyeong Ahn +1 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

CV-18 NER: Augmented Common Voice for Named Entity Recognition from Arabic Speech

End-to-end speech Named Entity Recognition (NER) aims to directly extract entities from speech. Prior work has shown that end-to-end (E2E) approaches can outperform cascaded pipelines for English, French, and Chinese, but Arabic remains under-explored due to its morphological complexity, the absence of short vowels, and limited annotated resources. We introduce CV-18 NER, the first publicly available dataset for NER from Arabic speech, created by augmenting the Arabic Common Voice 18 corpus with manual NER annotations following the fine-grained Wojood schema (21 entity types). We benchmark both pipeline systems (ASR + text NER) and E2E models based on Whisper and AraBEST-RQ. E2E systems substantially outperform the best pipeline configuration on the test set, reaching 37.0% CoER (AraBEST-RQ 300M) and 38.0% CVER (Whisper-medium). Further analysis shows that Arabic-specific self-supervised pretraining yields strong ASR performance, while multilingual weak supervision transfers more effectively to joint speech-to-entity learning, and that larger models may be harder to adapt in this low-resource setting. Our dataset and models are publicly released, providing the first open benchmark for end-to-end named entity recognition from Arabic speech https://huggingface.co/datasets/Elyadata/CV18-NER.

AI advanced Natural Language Processing
By: Youssef Saidi, Haroun Elleuch, Fethi Bougares
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

No Single Best Model for Diversity: Learning a Router for Sample Diversity

When posed with prompts that permit a large number of valid answers, comprehensively generating them is the first step towards satisfying a wide range of users. In this paper, we study methods to elicit a comprehensive set of valid responses. To evaluate this, we introduce \textbf{diversity coverage}, a metric that measures the total quality scores assigned to each \textbf{unique} answer in the predicted answer set relative to the best possible answer set with the same number of answers. Using this metric, we evaluate 18 LLMs, finding no single model dominates at generating diverse responses to a wide range of open-ended prompts. Yet, per each prompt, there exists a model that outperforms all other models significantly at generating a diverse answer set. Motivated by this finding, we introduce a router that predicts the best model for each query. On NB-Wildchat, our trained router outperforms the single best model baseline (26.3% vs $23.8%). We further show generalization to an out-of-domain dataset (NB-Curated) as well as different answer-generation prompting strategies. Our work lays foundation for studying generating comprehensive answers when we have access to a suite of models.

AI advanced Natural Language Processing
By: Yuhan Liu, Fangyuan Xu, Vishakh Padmakumar +2 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

Modular Energy Steering for Safe Text-to-Image Generation with Foundation Models

Controlling the behavior of text-to-image generative models is critical for safe and practical deployment. Existing safety approaches typically rely on model fine-tuning or curated datasets, which can degrade generation quality or limit scalability. We propose an inference-time steering framework that leverages gradient feedback from frozen pretrained foundation models to guide the generation process without modifying the underlying generator. Our key observation is that vision-language foundation models encode rich semantic representations that can be repurposed as off-the-shelf supervisory signals during generation. By injecting such feedback through clean latent estimates at each sampling step, our method formulates safety steering as an energy-based sampling problem. This design enables modular, training-free safety control that is compatible with both diffusion and flow-matching models and can generalize across diverse visual concepts. Experiments demonstrate state-of-the-art robustness against NSFW red-teaming benchmarks and effective multi-target steering, while preserving high generation quality on benign non-targeted prompts. Our framework provides a principled approach for utilizing foundation models as semantic energy estimators, enabling reliable and scalable safety control for text-to-image generation.

AI advanced Computer Vision
By: Yaoteng Tan, Zikui Cai, M. Salman Asif
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

Large-scale Codec Avatars: The Unreasonable Effectiveness of Large-scale Avatar Pretraining

High-quality 3D avatar modeling faces a critical trade-off between fidelity and generalization. On the one hand, multi-view studio data enables high-fidelity modeling of humans with precise control over expressions and poses, but it struggles to generalize to real-world data due to limited scale and the domain gap between the studio environment and the real world. On the other hand, recent large-scale avatar models trained on millions of in-the-wild samples show promise for generalization across a wide range of identities, yet the resulting avatars are often of low-quality due to inherent 3D ambiguities. To address this, we present Large-Scale Codec Avatars (LCA), a high-fidelity, full-body 3D avatar model that generalizes to world-scale populations in a feedforward manner, enabling efficient inference. Inspired by the success of large language models and vision foundation models, we present, for the first time, a pre/post-training paradigm for 3D avatar modeling at scale: we pretrain on 1M in-the-wild videos to learn broad priors over appearance and geometry, then post-train on high-quality curated data to enhance expressivity and fidelity. LCA generalizes across hair styles, clothing, and demographics while providing precise, fine-grained facial expressions and finger-level articulation control, with strong identity preservation. Notably, we observe emergent generalization to relightability and loose garment support to unconstrained inputs, and zero-shot robustness to stylized imagery, despite the absence of direct supervision.

AI advanced Computer Vision
By: Junxuan Li, Rawal Khirodkar, Chengan He +37 more
Source: arXiv Apr 2, 2026
0.0
10 min read
0
Quality
📄 paper

Beyond Referring Expressions: Scenario Comprehension Visual Grounding

Existing visual grounding benchmarks primarily evaluate alignment between image regions and literal referring expressions, where models can often succeed by matching a prominent named category. We explore a complementary and more challenging setting of scenario-based visual grounding, where the target must be inferred from roles, intentions, and relational context rather than explicit naming. We introduce Referring Scenario Comprehension (RSC), a benchmark designed for this setting. The queries in this benchmark are paragraph-length texts that describe object roles, user goals, and contextual cues, including deliberate references to distractor objects that often require deep understanding to resolve. Each instance is annotated with interpretable difficulty tags for uniqueness, clutter, size, overlap, and position which expose distinct failure modes and support fine-grained analysis. RSC contains approximately 31k training examples, 4k in-domain test examples, and a 3k out-of-distribution split with unseen object categories. We further propose ScenGround, a curriculum reasoning method serving as a reference point for this setting, combining supervised warm-starting with difficulty-aware reinforcement learning. Experiments show that scenario-based queries expose systematic failures in current models that standard benchmarks do not reveal, and that curriculum training improves performance on challenging slices and transfers to standard benchmarks.

AI advanced Computer Vision
By: Ruozhen He, Nisarg A. Shah, Qihua Dong +3 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

EventHub: Data Factory for Generalizable Event-Based Stereo Networks without Active Sensors

We propose EventHub, a novel framework for training deep-event stereo networks without ground truth annotations from costly active sensors, relying instead on standard color images. From these images, we derive either proxy annotations and proxy events through state-of-the-art novel view synthesis techniques, or simply proxy annotations when images are already paired with event data. Using the training set generated by our data factory, we repurpose state-of-the-art stereo models from RGB literature to process event data, obtaining new event stereo models with unprecedented generalization capabilities. Experiments on widely used event stereo datasets support the effectiveness of EventHub and show how the same data distillation mechanism can improve the accuracy of RGB stereo foundation models in challenging conditions such as nighttime scenes.

AI advanced Computer Vision
By: Luca Bartolomei, Fabio Tosi, Matteo Poggi +2 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

(PAC-)Learning state machines from data streams: A generic strategy and an improved heuristic (Extended version)

This is an extended version of our publication Learning state machines from data streams: A generic strategy and an improved heuristic, International Conference on Grammatical Inference (ICGI) 2023, Rabat, Morocco. It has been extended with a formal proof on PAC-bounds, and the discussion and analysis of a similar approach has been moved from the appendix and is now a full Section. State machines models are models that simulate the behavior of discrete event systems, capable of representing systems such as software systems, network interactions, and control systems, and have been researched extensively. The nature of most learning algorithms however is the assumption that all data be available at the beginning of the algorithm, and little research has been done in learning state machines from streaming data. In this paper, we want to close this gap further by presenting a generic method for learning state machines from data streams, as well as a merge heuristic that uses sketches to account for incomplete prefix trees. We implement our approach in an open-source state merging library and compare it with existing methods. We show the effectiveness of our approach with respect to run-time, memory consumption, and quality of results on a well known open dataset. Additionally, we provide a formal analysis of our algorithm, showing that it is capable of learning within the PAC framework, and show a theoretical improvement to increase run-time, without sacrificing correctness of the algorithm in larger sample sizes.

AI advanced Machine Learning
By: Robert Baumgartner, Sicco Verwer
Source: arXiv Apr 2, 2026
0.0
10 min read
0
Quality
📄 paper

BVFLMSP : Bayesian Vertical Federated Learning for Multimodal Survival with Privacy

Multimodal time-to-event prediction often requires integrating sensitive data distributed across multiple parties, making centralized model training impractical due to privacy constraints. At the same time, most existing multimodal survival models produce single deterministic predictions without indicating how confident the model is in its estimates, which can limit their reliability in real-world decision making. To address these challenges, we propose BVFLMSP, a Bayesian Vertical Federated Learning (VFL) framework for multimodal time-to-event analysis based on a Split Neural Network architecture. In BVFLMSP, each client independently models a specific data modality using a Bayesian neural network, while a central server aggregates intermediate representations to perform survival risk prediction. To enhance privacy, we integrate differential privacy mechanisms by perturbing client side representations before transmission, providing formal privacy guarantees against information leakage during federated training. We first evaluate our Bayesian multimodal survival model against widely used single modality survival baselines and the centralized multimodal baseline MultiSurv. Across multimodal settings, the proposed method shows consistent improvements in discrimination performance, with up to 0.02 higher C-index compared to MultiSurv. We then compare federated and centralized learning under varying privacy budgets across different modality combinations, highlighting the tradeoff between predictive performance and privacy. Experimental results show that BVFLMSP effectively includes multimodal data, improves survival prediction over existing baselines, and remains robust under strict privacy constraints while providing uncertainty estimates.

AI advanced Machine Learning
By: Abhilash Kar, Basisth Saha, Tanmay Sen +1 more
Source: arXiv Apr 2, 2026
0.0
10 min read
0
Quality
📄 paper

Smoothing the Landscape: Causal Structure Learning via Diffusion Denoising Objectives

Understanding causal dependencies in observational data is critical for informing decision-making. These relationships are often modeled as Bayesian Networks (BNs) and Directed Acyclic Graphs (DAGs). Existing methods, such as NOTEARS and DAG-GNN, often face issues with scalability and stability in high-dimensional data, especially when there is a feature-sample imbalance. Here, we show that the denoising score matching objective of diffusion models could smooth the gradients for faster, more stable convergence. We also propose an adaptive k-hop acyclicity constraint that improves runtime over existing solutions that require matrix inversion. We name this framework Denoising Diffusion Causal Discovery (DDCD). Unlike generative diffusion models, DDCD utilizes the reverse denoising process to infer a parameterized causal structure rather than to generate data. We demonstrate the competitive performance of DDCDs on synthetic benchmarking data. We also show that our methods are practically useful by conducting qualitative analyses on two real-world examples. Code is available at this url: https://github.com/haozhu233/ddcd.

AI advanced Machine Learning
By: Hao Zhu, Di Zhou, Donna Slonim
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

Model-Based Reinforcement Learning for Control under Time-Varying Dynamics

Learning-based control methods typically assume stationary system dynamics, an assumption often violated in real-world systems due to drift, wear, or changing operating conditions. We study reinforcement learning for control under time-varying dynamics. We consider a continual model-based reinforcement learning setting in which an agent repeatedly learns and controls a dynamical system whose transition dynamics evolve across episodes. We analyze the problem using Gaussian process dynamics models under frequentist variation-budget assumptions. Our analysis shows that persistent non-stationarity requires explicitly limiting the influence of outdated data to maintain calibrated uncertainty and meaningful dynamic regret guarantees. Motivated by these insights, we propose a practical optimistic model-based reinforcement learning algorithm with adaptive data buffer mechanisms and demonstrate improved performance on continuous control benchmarks with non-stationary dynamics.

AI advanced RoboticsMachine Learning
By: Klemens Iten, Bruce Lee, Chenhao Li +3 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

SKILL0: In-Context Agentic Reinforcement Learning for Skill Internalization

Agent skills, structured packages of procedural knowledge and executable resources that agents dynamically load at inference time, have become a reliable mechanism for augmenting LLM agents. Yet inference-time skill augmentation is fundamentally limited: retrieval noise introduces irrelevant guidance, injected skill content imposes substantial token overhead, and the model never truly acquires the knowledge it merely follows. We ask whether skills can instead be internalized into model parameters, enabling zero-shot autonomous behavior without any runtime skill retrieval. We introduce SKILL0, an in-context reinforcement learning framework designed for skill internalization. SKILL0 introduces a training-time curriculum that begins with full skill context and progressively withdraws it. Skills are grouped offline by category and rendered with interaction history into a compact visual context, teaching he model tool invocation and multi-turn task completion. A Dynamic Curriculum then evaluates each skill file's on-policy helpfulness, retaining only those from which the current policy still benefits within a linearly decaying budget, until the agent operates in a fully zero-shot setting. Extensive agentic experiments demonstrate that SKILL0 achieves substantial improvements over the standard RL baseline (+9.7\% for ALFWorld and +6.6\% for Search-QA), while maintaining a highly efficient context of fewer than 0.5k tokens per step. Our code is available at https://github.com/ZJU-REAL/SkillZero.

AI advanced Machine Learning
By: Zhengxi Lu, Zhiyuan Yao, Jinyang Wu +7 more
Source: arXiv Apr 2, 2026
0.0
10 min read
0
Quality
📄 paper

Taming the Exponential: A Fast Softmax Surrogate for Integer-Native Edge Inference

Softmax can become a computational bottleneck in the Transformer model's Multi-Head Attention (MHA) block, particularly in small models under low-precision inference, where exponentiation and normalization incur significant overhead. As such, we suggest using Head-Calibrated Clipped-Linear Softmax (HCCS), a bounded, monotone surrogate to the exponential softmax function, which uses a clipped linear mapping of the max centered attention logits. This approximation produces a stable probability distribution, maintains the ordering of the original logits and has non-negative values. HCCS differs from previous softmax surrogates as it includes a set of lightweight calibration parameters that are optimized offline based on a representative dataset and calibrated for each individual attention head to preserve the statistical properties of the individual heads. We describe a hardware-motivated implementation of HCCS for high-throughput scenarios targeting the AMD Versal AI Engines. The current reference implementations from AMD for this platform rely upon either bfloat16 arithmetic or LUTs to perform the exponential operation, which might limit the throughput of the platform and fail to utilize the high-throughput integer vector processing units of the AI Engine. In contrast, HCCS provides a natural mapping to the AI Engines' int8 multiply accumulate (MAC) units. To the best of our knowledge, this is the first int8 optimized softmax surrogate for AMD AI engines that significantly exceeds the speed performance of other reference implementations while maintaining competitive task accuracy on small or heavily quantized MHA workloads after quantization-aware retraining.

AI advanced Machine Learning
By: Dimitrios Danopoulos, Enrico Lupi, Michael Kagan +1 more
Source: arXiv Apr 2, 2026
0.0
10 min read
0
Quality
📄 paper

go-$m$HC: Direct Parameterization of Manifold-Constrained Hyper-Connections via Generalized Orthostochastic Matrices

Doubly stochastic matrices enable learned mixing across residual streams, but parameterizing the set of doubly stochastic matrices (the Birkhoff polytope) exactly and efficiently remains an open challenge. Existing exact methods scale factorially with the number of streams ($d$), while Kronecker-factorized approaches are efficient but expressivity-limited. We introduce a novel exact parameterization grounded in the theory of generalized orthostochastic matrices, which scales as $\mathcal{O}(d^3)$ and exposes a single hyperparameter $s$ which continuously interpolates between a computationally efficient boundary and the fully expressive Birkhoff polytope. Building on Manifold-Constrained Hyper-Connections ($m$HC), a framework for learned dynamic layer connectivity, we instantiate this parameterization in go-$m$HC. Our method composes naturally with Kronecker-factorized methods, substantially recovering expressivity at similar FLOP costs. Spectral analysis indicates that go-$m$HC fills the Birkhoff polytope far more completely than Kronecker-factorized baselines. On synthetic stream-mixing tasks, go-$m$HC achieves the minimum theoretical loss while converging up to $10\times$ faster. We validate our approach in a 30M parameter GPT-style language model. The expressivity, efficiency, and exactness of go-$m$HC offer a practical avenue for scaling $d$ as a new dimension of model capacity.

AI advanced Natural Language ProcessingMachine Learning
By: Torque Dandachi, Sophia Diggs-Galligan
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

Topological Effects in Neural Network Field Theory

Neural network field theory formulates field theory as a statistical ensemble of fields defined by a network architecture and a density on its parameters. We extend the construction to topological settings via the inclusion of discrete parameters that label the topological quantum number. We recover the Berezinskii--Kosterlitz--Thouless transition, including the spin-wave critical line and the proliferation of vortices at high temperatures. We also verify the T-duality of the bosonic string, showing invariance under the exchange of momentum and winding on $S^1$, the transformation of the sigma model couplings according to the Buscher rules on constant toroidal backgrounds, the enhancement of the current algebra at self-dual radius, and non-geometric T-fold transition functions.

AI advanced Machine Learning
By: Christian Ferko, James Halverson, Vishnu Jejjala +1 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

Do Emotions in Prompts Matter? Effects of Emotional Framing on Large Language Models

Emotional tone is pervasive in human communication, yet its influence on large language model (LLM) behaviour remains unclear. Here, we examine how first-person emotional framing in user-side queries affect LLM performance across six benchmark domains, including mathematical reasoning, medical question answering, reading comprehension, commonsense reasoning and social inference. Across models and tasks, static emotional prefixes usually produce only small changes in accuracy, suggesting that affective phrasing is typically a mild perturbation rather than a reliable general-purpose intervention. This stability is not uniform: effects are more variable in socially grounded tasks, where emotional context more plausibly interacts with interpersonal reasoning. Additional analyses show that stronger emotional wording induces only modest extra change, and that human-written prefixes reproduce the same qualitative pattern as LLM-generated ones. We then introduce EmotionRL, an adaptive emotional prompting framework that selects emotional framing adaptively for each query. Although no single emotion is consistently beneficial, adaptive selection yields more reliable gains than fixed emotional prompting. Together, these findings show that emotional tone is neither a dominant driver of LLM performance nor irrelevant noise, but a weak and input-dependent signal that can be exploited through adaptive control.

AI advanced Artificial Intelligence
By: Minda Zhao, Yutong Yang, Chufei Peng +5 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

Retrieval-Augmented Question Answering over Scientific Literature for the Electron-Ion Collider

To harness the power of Language Models in answering domain specific specialized technical questions, Retrieval Augmented Generation (RAG) is been used widely. In this work, we have developed a Q\&A application inspired by the Retrieval Augmented Generation (RAG), which is comprised of an in-house database indexed on the arXiv articles related to the Electron-Ion Collider (EIC) experiment - one of the largest international scientific collaboration and incorporated an open-source LLaMA model for answer generation. This is an extension to it's proceeding application built on proprietary model and Cloud-hosted external knowledge-base for the EIC experiment. This locally-deployed RAG-system offers a cost-effective, resource-constraint alternative solution to build a RAG-assisted Q\&A application on answering domain-specific queries in the field of experimental nuclear physics. This set-up facilitates data-privacy, avoids sending any pre-publication scientific data and information to public domain. Future improvement will expand the knowledge base to encompass heterogeneous EIC-related publications and reports and upgrade the application pipeline orchestration to the LangGraph framework.

AI advanced Artificial Intelligence
By: Tina. J. Jat, T. Ghosh, Karthik Suresh
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

Crystalite: A Lightweight Transformer for Efficient Crystal Modeling

Generative models for crystalline materials often rely on equivariant graph neural networks, which capture geometric structure well but are costly to train and slow to sample. We present Crystalite, a lightweight diffusion Transformer for crystal modeling built around two simple inductive biases. The first is Subatomic Tokenization, a compact chemically structured atom representation that replaces high-dimensional one-hot encodings and is better suited to continuous diffusion. The second is the Geometry Enhancement Module (GEM), which injects periodic minimum-image pair geometry directly into attention through additive geometric biases. Together, these components preserve the simplicity and efficiency of a standard Transformer while making it better matched to the structure of crystalline materials. Crystalite achieves state-of-the-art results on crystal structure prediction benchmarks, and de novo generation performance, attaining the best S.U.N. discovery score among the evaluated baselines while sampling substantially faster than geometry-heavy alternatives.

AI advanced Artificial IntelligenceMachine Learning
By: Tin Hadži Veljković, Joshua Rosenthal, Ivor Lončarić +1 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

Unifying Group-Relative and Self-Distillation Policy Optimization via Sample Routing

Reinforcement learning with verifiable rewards (RLVR) has become a standard paradigm for post-training large language models. While Group Relative Policy Optimization (GRPO) is widely adopted, its coarse credit assignment uniformly penalizes failed rollouts, lacking the token-level focus needed to efficiently address specific deviations. Self-Distillation Policy Optimization (SDPO) addresses this by providing denser, more targeted logit-level supervision that facilitates rapid early improvement, yet it frequently collapses during prolonged training. We trace this late-stage instability to two intrinsic flaws: self-distillation on already-correct samples introduces optimization ambiguity, and the self-teacher's signal reliability progressively degrades. To resolve these issues, we propose Sample-Routed Policy Optimization (SRPO), a unified on-policy framework that routes correct samples to GRPO's reward-aligned reinforcement and failed samples to SDPO's targeted logit-level correction. SRPO further incorporates an entropy-aware dynamic weighting mechanism to suppress high-entropy, unreliable distillation targets while emphasizing confident ones. Evaluated across five benchmarks and two model scales, SRPO achieves both the rapid early improvement of SDPO and the long-horizon stability of GRPO. It consistently surpasses the peak performance of both baselines, raising the five-benchmark average on Qwen3-8B by 3.4% over GRPO and 6.3% over SDPO, while simultaneously yielding moderate response lengths and lowering per-step compute cost by up to 17.2%.

AI advanced Artificial IntelligenceMachine Learning
By: Gengsheng Li, Tianyu Yang, Junfeng Fang +6 more
Source: arXiv Apr 2, 2026
0.0
10 min read
0
Quality
📄 paper

Omni123: Exploring 3D Native Foundation Models with Limited 3D Data by Unifying Text to 2D and 3D Generation

Recent multimodal large language models have achieved strong performance in unified text and image understanding and generation, yet extending such native capability to 3D remains challenging due to limited data. Compared to abundant 2D imagery, high-quality 3D assets are scarce, making 3D synthesis under-constrained. Existing methods often rely on indirect pipelines that edit in 2D and lift results into 3D via optimization, sacrificing geometric consistency. We present Omni123, a 3D-native foundation model that unifies text-to-2D and text-to-3D generation within a single autoregressive framework. Our key insight is that cross-modal consistency between images and 3D can serve as an implicit structural constraint. By representing text, images, and 3D as discrete tokens in a shared sequence space, the model leverages abundant 2D data as a geometric prior to improve 3D representations. We introduce an interleaved X-to-X training paradigm that coordinates diverse cross-modal tasks over heterogeneous paired datasets without requiring fully aligned text-image-3D triplets. By traversing semantic-visual-geometric cycles (e.g., text to image to 3D to image) within autoregressive sequences, the model jointly enforces semantic alignment, appearance fidelity, and multi-view geometric consistency. Experiments show that Omni123 significantly improves text-guided 3D generation and editing, demonstrating a scalable path toward multimodal 3D world models.

AI advanced Artificial IntelligenceComputer Vision
By: Chongjie Ye, Cheng Cao, Chuanyu Pan +4 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

VOID: Video Object and Interaction Deletion

Existing video object removal methods excel at inpainting content "behind" the object and correcting appearance-level artifacts such as shadows and reflections. However, when the removed object has more significant interactions, such as collisions with other objects, current models fail to correct them and produce implausible results. We present VOID, a video object removal framework designed to perform physically-plausible inpainting in these complex scenarios. To train the model, we generate a new paired dataset of counterfactual object removals using Kubric and HUMOTO, where removing an object requires altering downstream physical interactions. During inference, a vision-language model identifies regions of the scene affected by the removed object. These regions are then used to guide a video diffusion model that generates physically consistent counterfactual outcomes. Experiments on both synthetic and real data show that our approach better preserves consistent scene dynamics after object removal compared to prior video object removal methods. We hope this framework sheds light on how to make video editing models better simulators of the world through high-level causal reasoning.

AI advanced Artificial IntelligenceComputer Vision
By: Saman Motamed, William Harvey, Benjamin Klein +3 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📄 paper

ActionParty: Multi-Subject Action Binding in Generative Video Games

Recent advances in video diffusion have enabled the development of "world models" capable of simulating interactive environments. However, these models are largely restricted to single-agent settings, failing to control multiple agents simultaneously in a scene. In this work, we tackle a fundamental issue of action binding in existing video diffusion models, which struggle to associate specific actions with their corresponding subjects. For this purpose, we propose ActionParty, an action controllable multi-subject world model for generative video games. It introduces subject state tokens, i.e. latent variables that persistently capture the state of each subject in the scene. By jointly modeling state tokens and video latents with a spatial biasing mechanism, we disentangle global video frame rendering from individual action-controlled subject updates. We evaluate ActionParty on the Melting Pot benchmark, demonstrating the first video world model capable of controlling up to seven players simultaneously across 46 diverse environments. Our results show significant improvements in action-following accuracy and identity consistency, while enabling robust autoregressive tracking of subjects through complex interactions.

AI advanced Artificial IntelligenceComputer Vision
By: Alexander Pondaven, Ziyi Wu, Igor Gilitschenski +4 more
Source: arXiv Apr 2, 2026
0.0
5 min read
0
Quality
📰 news

Google’s new Gemma 4 models bring complex reasoning skills to low-power devices

Google LLC is upping the stakes for open-weights artificial intelligence models with the release of Gemma 4, its most advanced “open” model family so far. Built on the same architectural foundation as Gemini 3, the models are designed to handle complex reason…

AI beginner AI Products
By: Mike Wheatley
Source: NewsAPI Apr 2, 2026
4.0
1 min read
0
Quality
📰 news

Microsoft launches 3 AI models for transcription, image, and speech generation

Through these three models — MAI-Transcribe-1, MAI-Voice-1, and MAI-Image-2 — Microsoft aims to expand its push into multimodal AI capabilities for developers. The models are also being integrated into Microsoft products, including Copilot, Bing, and PowerPoi…

AI beginner AI Products
By: ETtech
Source: NewsAPI Apr 2, 2026
4.0
1 min read
0
Quality
🎥 video

Artificial Intelligence Jobs Unlocked: Pathways to the Future

Artificial intelligence jobs are reshaping industries—from health care and finance to robotics and marketing. In this video, explore high-demand AI roles, the skills employers look for, and practical steps to begin building a future in artificial intelligence. Whether the goal is to become a machine learning engineer, data scientist, AI developer, or robotics engineer, discover how to develop in-demand skills, gain hands-on experience, and stay competitive in a fast-moving field. 00:00 Introdu

AI beginner Machine Learning
By: Coursera
Source: YouTube AI Channels Apr 3, 2026
2.0
57
Quality
🎥 video

YOLO-World: Real-Time, Zero-Shot Object Detection Explained

In this video, you’ll learn how to use YOLO-World, a cutting-edge zero-shot object detection model. We'll cover its speed, compare it to other models, and run a live code demo for image AND video analysis. Chapters: - 00:00 Intro - 00:42 YOLO-World vs. Traditional Object Detectors: Speed and Accuracy - 02:26 YOLO-World Architecture - prompt-then-detect - 03:59 Setting Up and Running YOLO-World - 05:33 Prompt Engineering and Detections Post-Processing - 09:20 Video Processing with YOLO-World -

AI beginner Computer VisionReinforcement Learning
By: Roboflow
Source: YouTube AI Channels Feb 21, 2024
2.0
59,203
Quality
🎥 video

What is Computer Vision? | Artificial Intelligence for Beginners | Tamil | Karthik's Show

This video explains in Tamil, What is Computer Vision and science behind how it works. Please go through the links provided in this description below for more details. Subscribe to this channel for more such videos. Deep Learning explained : https://youtu.be/9gRyL5j3NUM Check 'Python Programming for Beginners' Tamil course at https://www.karthiksshow.com/courses/Python-Programming-for-Beginners-638dbf0ce4b09464540754a9. Check 'Python Programming for Machine Learning' Tamil course at https://

AI beginner Machine LearningDeep Learning
By: Karthik's Show
Source: YouTube AI Channels Apr 20, 2024
2.3
12,785
Quality
📝 blog

From RTX to Spark: NVIDIA Accelerates Gemma 4 for Local Agentic AI

Open models are driving a new wave of on-device AI, extending innovation beyond the cloud to everyday devices. As these models advance, their value increasingly depends on access to local, real-time context that can turn meaningful insights into action.  Designed for this shift, Google’s latest additions to the Gemma 4 family introduce a class of small, fast and omni-capable models built for efficient local execution across a wide range […]

AI intermediate AI ResearchGPU Computing
By: Michael Fukuyama
Source: NVIDIA AI Blog Apr 2, 2026
0.0
1 min read
0
Quality
📝 blog

Linear Regression Is Actually a Projection Problem (Part 2: From Projections to Predictions)

The Vector View of Least Squares. The post Linear Regression Is Actually a Projection Problem (Part 2: From Projections to Predictions) appeared first on Towards Data Science.

AI intermediate Data ScienceMachine Learning
By: Nikhil Dasari
Source: Towards Data Science Apr 2, 2026
0.0
1 min read
0
Quality
📝 blog

DenseNet Paper Walkthrough: All Connected

When we try to train a very deep neural network model, one issue that we might encounter is the vanishing gradient problem. This is essentially a problem where the weight update of a model during training slows down or even stops, hence causing the model not to improve. When a network is very deep, the […] The post DenseNet Paper Walkthrough: All Connected appeared first on Towards Data Science.

AI intermediate Data ScienceMachine Learning
By: Muhammad Ardi
Source: Towards Data Science Apr 3, 2026
0.0
1 min read
0
Quality