Hunyuan3D-Buffalo 1.0: A Unified Multimodal Model for Scalable 3D Generation, Understanding, and Editing Paper • 2608.02711 • Published 6 days ago • 83
Stale but Stable: Staleness-Adaptive Trust Regions for Stabilizing Asynchronous Reinforcement Learning Paper • 2607.18722 • Published 19 days ago • 35
Long-Horizon-Terminal-Bench: Testing the Limits of Agents on Long-Horizon Terminal Tasks with Dense Reward-Based Grading Paper • 2607.08964 • Published Jul 9 • 77
TurnOPD: Making On-Policy Distillation Turn-Aware for Efficient Long-Horizon Agent Training Paper • 2607.05804 • Published Jul 7 • 19
Hierarchical Sparse Attention Done Right: Toward Infinite Context Modeling Paper • 2607.02980 • Published Jul 3 • 84
When Search Agents Should Ask: DiscoBench for Clarification-Aware Deep Search Paper • 2606.27669 • Published Jun 26 • 16
Optimizing Visual Generative Models via Distribution-wise Rewards Paper • 2607.02291 • Published Jul 2 • 18
GEAR: Guided End-to-End AutoRegression for Image Synthesis Paper • 2606.32039 • Published Jun 30 • 34
PolyFlow: Continuous Topology Embedding Flow Matching for Artist-style Mesh Generation Paper • 2606.30673 • Published Jun 25 • 12
GUICrafter: Weakly-Supervised GUI Agent Leveraging Massive Unannotated Screenshots Paper • 2606.29705 • Published Jun 29 • 16
ViQ: Text-Aligned Visual Quantized Representations at Any Resolution Paper • 2606.27313 • Published Jun 25 • 38
VeriEvol: Scaling Multimodal Mathematical Reasoning via Verifiable Evol-Instruct Paper • 2606.23543 • Published Jun 22 • 6
FastMix: Fast Data Mixture Optimization via Gradient Descent Paper • 2606.14971 • Published Jun 12 • 3
STARE: Surprisal-Guided Token-Level Advantage Reweighting for Policy Entropy Stability Paper • 2606.19236 • Published Jun 17 • 13
Stream3D-VLM: Online 3D Spatial Understanding with Incremental Geometry Priors Paper • 2606.06891 • Published Jun 5 • 4