Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents

EVA: Efficient Reinforcement Learning for End-to-End Video Agent

Foveated Diffusion: Efficient Spatially Adaptive Image and Video Generation

Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

PEARL: Personalized Streaming Video Understanding Model

WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost

F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting

SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models

PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow

LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation

Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer

Why Does Self-Distillation (Sometimes) Degrade the Reasoning Capability of LLMs?

UI-Voyager: A Self-Evolving GUI Agent Learning via Failed Experience

T-MAP: Red-Teaming LLM Agents with Trajectory-aware Evolutionary Search

CUA-Suite: Massive Human-annotated Video Demonstrations for Computer-Use Agents

EVA: Efficient Reinforcement Learning for End-to-End Video Agent

Foveated Diffusion: Efficient Spatially Adaptive Image and Video Generation

Ego2Web: A Web Agent Benchmark Grounded in Egocentric Videos

From Static Templates to Dynamic Runtime Graphs: A Survey of Workflow Optimization for LLM Agents

SpecEyes: Accelerating Agentic Multimodal LLMs via Speculative Perception and Planning

DA-Flow: Degradation-Aware Optical Flow Estimation with Diffusion Models

PEARL: Personalized Streaming Video Understanding Model

WildWorld: A Large-Scale Dataset for Dynamic World Modeling with Actions and Explicit State toward Generative ARPG

MinerU-Diffusion: Rethinking Document OCR as Inverse Rendering via Diffusion Decoding

PivotRL: High Accuracy Agentic Post-Training at Low Compute Cost

F4Splat: Feed-Forward Predictive Densification for Feed-Forward 3D Gaussian Splatting

SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning

VideoDetective: Clue Hunting via both Extrinsic Query and Intrinsic Relevance for Long Video Understanding

LongCat-Flash-Prover: Advancing Native Formal Reasoning via Agentic Tool-Integrated Reinforcement Learning

Speed by Simplicity: A Single-Stream Architecture for Fast Audio-Video Generative Foundation Model

Omni-WorldBench: Towards a Comprehensive Interaction-Centric Evaluation for World Models

PrismAudio: Decomposed Chain-of-Thoughts and Multi-dimensional Rewards for Video-to-Audio Generation

LeWorldModel: Stable End-to-End Joint-Embedding Predictive Architecture from Pixels

FlowScene: Style-Consistent Indoor Scene Generation with Multimodal Graph Rectified Flow

LumosX: Relate Any Identities with Their Attributes for Personalized Video Generation

The Y-Combinator for LLMs: Solving Long-Context Rot with λ-Calculus

ProactiveBench: Benchmarking Proactiveness in Multimodal Large Language Models

TerraScope: Pixel-Grounded Visual Reasoning for Earth Observation

Astrolabe: Steering Forward-Process Reinforcement Learning for Distilled Autoregressive Video Models

HopChain: Multi-Hop Data Synthesis for Generalizable Vision-Language Reasoning

Bridging Semantic and Kinematic Conditions with Diffusion-based Discrete Motion Tokenizer