Ask Before You Optimize: Dynamic Pre-Formulation Clarification for Interactive Optimization Paper • 2609.05258 • Published 20 days ago • 20
TurboVLA: Real-Time Vision-Language-Action Model at 32 Hz on an RTX 4090 with <1 GB VRAM Paper • 2607.27205 • Published Jul 29 • 69
SEED: Self-Evolving On-Policy Distillation for Agentic Reinforcement Learning Paper • 2607.14777 • Published Jul 16 • 104
SAM-MT: Real-Time Interactive Multi-Target Video Segmentation Paper • 2607.08688 • Published Jul 9 • 8
Delayed Verification Destabilizes Multi-Agent LLM Belief: Instability Thresholds and Optimal Corrector Placement Paper • 2606.27409 • Published Jun 25 • 4
Beyond Static Leaderboards: Predictive Validity for the Evaluation of LLM Agents Paper • 2606.19704 • Published Jun 18 • 43
Imaginative Perception Tokens Enhance Spatial Reasoning in Multimodal Language Models Paper • 2606.03988 • Published Jun 3 • 26
SCOPE: Self-Play via Co-Evolving Policies for Open-Ended Tasks Paper • 2605.31433 • Published May 29 • 26
RoboStressBench: Benchmarking VLM Robustness to Physical Visual Stress in Embodied Scenes Paper • 2606.00828 • Published May 30 • 9
Gamma-World: Generative Multi-Agent World Modeling Beyond Two Players Paper • 2605.28816 • Published May 27 • 149
Perception or Prejudice: Can MLLMs Go Beyond First Impressions of Personality? Paper • 2605.22109 • Published May 21 • 50
GameWorld: Towards Standardized and Verifiable Evaluation of Multimodal Game Agents Paper • 2604.07429 • Published Apr 8 • 63
ShotStream: Streaming Multi-Shot Video Generation for Interactive Storytelling Paper • 2603.25746 • Published Mar 26 • 44
SocialOmni: Benchmarking Audio-Visual Social Interactivity in Omni Models Paper • 2603.16859 • Published Mar 17 • 48