/// AI HUB
Dashboard News Models Tools Papers Repos Videos Companies Trending
Login

Research Papers

Latest AI/ML research from ArXiv and Papers with Code

Latest Trending
Papers with Code paper Sep 30

Learning Chaos Without Seeing Chaos: Extrapolation of Global Dynamics in Autoregressive Transformers

Autoregressive models are trained to predict a system's behavior one step at a time, and recursive generation allows the learned dynamics to unfold over long horizons. To what exte...

21
Papers with Code paper Sep 30

OmniReasoning: Pushing the Limits of Audio-Visual Joint Reasoning

Recent advances have enabled unified omni-modal models in understanding audio, vision, and language. However, existing benchmarks, training data, and learning methods largely treat...

21
Papers with Code paper Sep 30

PhysVista: Benchmarking Physical Intelligence in VLMs via a Perception-Reasoning-Assessment Loop

Vision-Language Models (VLMs) have shown strong multimodal reasoning capabilities, yet whether they truly capture the physical consistency underlying real-world dynamics remains un...

21
Papers with Code paper Sep 30

SemanTok: Predictable Semantic Tokens for Efficient Autoregressive Video Generation

Recent video-based world models pair the scalability of autoregressive (AR) prediction with the visual quality of diffusion models. The choice of scene tokenizer is paramount for t...

21
Papers with Code paper Sep 30

MemLife: Curating and Reasoning over Long-Term Egocentric Video Memories

Long-term egocentric video enables personalized AI assistants to reason about daily life. However, as video histories grow to hundreds of hours spanning months or years, reprocessi...

21
Papers with Code paper Sep 30

Does Learning Protein Folding Generalize to Broader Reasoning?

Large language models rely heavily on human text, which often conveys surface answers rather than the spatial and structural logic behind them. Protein folding is a natural testbed...

21
Papers with Code paper Sep 30

LexReward: A Taxonomy-Driven Reward Framework for Legal Language Models

Legal language models require reward signals that capture not only answer correctness but also the multidimensional quality of legal responses. Existing reward methods, however, of...

21
Papers with Code paper Sep 30

SpatialCORE: Confidence-Aware Grounded Spatial Reasoning in Large Vision--Language Models

Large Vision-Language Models (LVLMs) have made remarkable progress across visual perception tasks, yet spatial reasoning remains a persistent weakness, especially for questions tha...

Multimodal
21
Papers with Code paper Sep 30

From Given to Gathered Evidence: Agentic Learning for Longitudinal Medical Reasoning

Foundation models can serve as clinical agents through tool-use harnesses. However, conventional medical benchmarks assess reasoning over preselected evidence rather than the abili...

Agents
21
Papers with Code paper Sep 30

I Have a Stream: Making Self-Supervised Learning Work on Continuous Video

Self-supervised learning draws inspiration from infant visual development, yet standard training pipelines bear little resemblance to it: images are independently sampled and globa...

21
Papers with Code paper Sep 30

Video Generation Models: A Survey of Post-Training and Alignment

Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamics. Despite strong generative pr...

Safety/Alignment
21
Papers with Code paper Sep 30

The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends

Self-attention gives LLMs fine-grained, query-dependent access to context, but dense token interactions incur quadratic prefill cost and a key--value cache growing with context len...

21
Papers with Code paper Sep 30

Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated Papers

AI-generated content, often called AI slop, is increasingly common everywhere, particularly in academia. Slop in AI-generated scientific papers, however, has more complex patterns ...

21
Papers with Code paper Sep 30

Training LLM Judges from Language Feedback via Position-Selective Self-Distillation

We study training LLM judges from natural language feedback, especially for subjective tasks where the verdict depends strongly on which evaluation criteria the judge invokes and h...

LLM
21
Papers with Code paper Sep 30

FrameMorrow: Future-guided Frame Selection with Prospective Tokens for Long-Horizon Video Generation

Long-horizon video generation requires models to effectively leverage an increasingly long generation history. As the generated history grows, retaining all previous content become...

21
Papers with Code paper Sep 30

Covert Assistance: Helpful LLM Agents Evade Oversight in Multi-Agent Systems

As multi-agent systems enter high-stakes domains, the possibility that agents may circumvent safety boundaries is a growing concern. Prior work has examined this risk primarily in ...

LLM
21
Papers with Code paper Sep 30

DEFINE: Exemplar-Guided Accent Control for Zero-Shot TTS

Zero-shot text-to-speech (TTS) can reproduce an unseen speaker from a short reference recording, but typically entangles speaker identity and accent within the same reference. We i...

21
Papers with Code paper Sep 30

Diptych: Scoped, AI-Interpreted Comparison for Reference Listening in Music Production

Reference listening is a common strategy in music production, but current comparison tools often obscure a key human judgment: deciding what should be compared. We present Diptych,...

21
Papers with Code paper Sep 30

How Much Is an AI Token Worth? Scaling Laws for Wild AI-Generated Web Text

Web text makes up the majority of pretraining data and is increasingly AI-generated. After applying FineWeb quality filtering, we find that 27.5% of tokens from June 2026 web data ...

21
Papers with Code paper Sep 30

LEAP: Learned Block-wise Evidence Retrieval for Long Audio-Video Perception

Hour-scale audio-visual question answering is constrained by a context dilemma: dense whole-recording encoding rapidly exhausts context limits, whereas uniform temporal compression...

21
Papers with Code paper Sep 30

Removing Timing Shortcuts Improves Non-Invasive Brain-to-Text

We find that major reported improvements in decoding words from non-invasive brain recordings are largely reproducible without any brain data. In the influential work of d'Ascoli e...

21
Papers with Code paper Sep 30

Multimodal Flow: Unified Flow Modeling of Language and Vision in Embedding Spaces

We present Multimodal Flow, a fully continuous generative model of language and vision. Most unified multimodal models either model both language and quantized images as discrete t...

Multimodal
21
Papers with Code paper Sep 30

Make Sparse Rewards Count: Density-Aware Reward Aggregation for Multi-Reward RL

Multi-reward reinforcement learning trains large language models to satisfy multiple behavioral objectives simultaneously. Reward-wise normalization, as used in GDPO, preserves rew...

21
Papers with Code paper Sep 30

QuantMLA: Function-Aligned Dual-Path Quantization for Low-Bit MLA KV Caching

Multi-Head Latent Attention (MLA) enables expressive multi-head attention with compact caches for its content and decoupled RoPE paths, yet cache memory still scales linearly with ...

21
« Previous Page 72 of 292 (6991 items) Next »
AI Hub // AI Intelligence Platform // LIVE FEED // Impressum // Datenschutz © 2026
0 new articles available