Hallucinations Undermine Trust; Metacognition is a Way Forward

X2SAM: Any Segmentation in Images and Videos

OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories

PRISM: Pre-alignment via Black-box On-policy Distillation for Multimodal Reinforcement Learning

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

ProgramBench: Can Language Models Rebuild Programs From Scratch?

Efficient Accelerated Graph Edit Distance Computation on GPU

LLM-based uncertainty assessment of social media situational signals for crisis reporting

Canonical LST: A Protocol-Native Liquid Staking Solution for Tezos

Separating Intelligence from Execution: A Workflow Engine for the Model Context Protocol

Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs

EnergAIzer: Fast and Accurate GPU Power Estimation Framework for AI Workloads

Leveraging Verifier-Based Reinforcement Learning in Image Editing

Efficient Training on Multiple Consumer GPUs with RoundPipe

ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control

Co-Evolving Policy Distillation

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Heterogeneous Scientific Foundation Model Collaboration

Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion

RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments

ClawGym: A Scalable Framework for Building Effective Claw Agents

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

Large Language Models Explore by Latent Distilling

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

SWE-chat: Coding Agent Interactions From Real Users in the Wild

AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation

Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models

AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

Meta-CoT: Enhancing Granularity and Generalization in Image Editing

Hallucinations Undermine Trust; Metacognition is a Way Forward

X2SAM: Any Segmentation in Images and Videos

OpenSeeker-v2: Pushing the Limits of Search Agents with Informative and High-Difficulty Trajectories

PRISM: Pre-alignment via Black-box On-policy Distillation for Multimodal Reinforcement Learning

ARIS: Autonomous Research via Adversarial Multi-Agent Collaboration

ProgramBench: Can Language Models Rebuild Programs From Scratch?

Efficient Accelerated Graph Edit Distance Computation on GPU

LLM-based uncertainty assessment of social media situational signals for crisis reporting

Canonical LST: A Protocol-Native Liquid Staking Solution for Tezos

Separating Intelligence from Execution: A Workflow Engine for the Model Context Protocol

Understanding the Performance Plateau in Text-to-Video Retrieval: A Comprehensive Empirical and Linguistic Analysis

Persistent Visual Memory: Sustaining Perception for Deep Generation in LVLMs

EnergAIzer: Fast and Accurate GPU Power Estimation Framework for AI Workloads

Leveraging Verifier-Based Reinforcement Learning in Image Editing

Efficient Training on Multiple Consumer GPUs with RoundPipe

ExoActor: Exocentric Video Generation as Generalizable Interactive Humanoid Control

Co-Evolving Policy Distillation

Visual Generation in the New Era: An Evolution from Atomic Mapping to Agentic World Modeling

Heterogeneous Scientific Foundation Model Collaboration

Diffusion Templates: A Unified Plugin Framework for Controllable Diffusion

RADIO-ViPE: Online Tightly Coupled Multi-Modal Fusion for Open-Vocabulary Semantic SLAM in Dynamic Environments

ClawGym: A Scalable Framework for Building Effective Claw Agents

Turning the TIDE: Cross-Architecture Distillation for Diffusion Large Language Models

Large Language Models Explore by Latent Distilling

GLM-5V-Turbo: Toward a Native Foundation Model for Multimodal Agents

SWE-chat: Coding Agent Interactions From Real Users in the Wild

AdaExplore: Failure-Driven Adaptation and Diversity-Preserving Search for Efficient Kernel Generation

Refinement via Regeneration: Enlarging Modification Space Boosts Image Refinement in Unified Multimodal Models

AutoResearchBench: Benchmarking AI Agents on Complex Scientific Literature Discovery

Meta-CoT: Enhancing Granularity and Generalization in Image Editing