Trajectory2Gym: Decision-Grounded Compositional Interaction Synthesis for Tool-Use Agents Paper • 2610.33568 • Published 4 days ago • 354
Eat Your Precision: Precision Objective Mitigates Reward Hacking in Rubric-based RL Paper • 2610.33512 • Published 4 days ago • 42
WorldCast: World-Consistent Character Video Generation with Large-Angle Camera Control Paper • 2610.33135 • Published 5 days ago • 51
Rethinking Video Storage for AI Training: Breaking Cross-Frame Dependencies for Efficient Random Access Paper • 2610.33079 • Published 7 days ago • 16
Mycelium: A Meta-Study of Hallucination Detection Across Provenance, Typology, and Granularities Paper • 2610.33608 • Published 4 days ago • 14
SliderEdit++: Improved Slider Trajectories in Instruction-Based Image Editing Paper • 2610.14253 • Published 14 days ago • 16
HiSTEVE 1.0: Harnessing Human-Interface VLA Agents for Open-World Games Paper • 2610.31162 • Published 6 days ago • 57
MMVistaReason: Toward Open-Data and Post-Training Recipes for Multimodal Reasoning Paper • 2610.01352 • Published 6 days ago • 16
RouteWeaver: Weaving Mode Selection and Execution into Unified LLM Routing Paper • 2610.19705 • Published 9 days ago • 32
Heartbeat Thinking: Speculative Reasoning and Tool Execution While Listening in Realtime Voice Agents Paper • 2610.26233 • Published 9 days ago • 36
Deep Fusion Memory: A Chunk-Level Parametric Memory for Large Language Models Paper • 2610.25100 • Published 10 days ago • 61
AgentVQA: A Unified Benchmark for Agentic Visual Understanding Paper • 2610.31494 • Published 6 days ago • 25
SCOPE: Compiling Natural-Language Policies into Neurosymbolic Predicate Programs Paper • 2610.31062 • Published 6 days ago • 32
VerifierBench: Benchmarking the Generation of Executable Verifiers for LLM Agents Paper • 2610.28679 • Published 9 days ago • 32
RoAR-VAE: Improving Latent Diffusability through Robust Prediction Paper • 2610.26216 • Published 9 days ago • 42
EvaOmni: An Evidence-Grounded Benchmark for Audio-Visual Reasoning Paper • 2610.28444 • Published 8 days ago • 28
RealMe: Immersive Volumetric Video from Minimal Captures Paper • 2610.30023 • Published 7 days ago • 28
PrismaCoder: Pushing the Boundaries of Open Multimodal Code Intelligence through Decomposed Rubric Synthesis Paper • 2610.20538 • Published 14 days ago • 72