Submitted by zhangysk 61 TreePO: Bridging the Gap of Policy Optimization and Efficacy and Inference Efficiency with Heuristic Tree-based Modeling · 17 authors 13 3
Submitted by weidawang 43 CMPhysBench: A Benchmark for Evaluating Large Language Models in Condensed Matter Physics · 35 authors 16 2
Submitted by huanngzh 29 VoxHammer: Training-Free Precise and Coherent 3D Editing in Native 3D Space · 7 authors 60 2
Submitted by taesiri 28 OmniHuman-1.5: Instilling an Active Mind in Avatars via Cognitive Simulation · 9 authors 2
Submitted by taesiri 23 UltraMemV2: Memory Networks Scaling to 120B Parameters with Superior Long-Context Learning · 11 authors 7 2
Submitted by vlongle 21 Pixie: Fast and Generalizable Supervised Learning of 3D Physics from Pixels · 7 authors 50 2
Submitted by MoonQiu 14 CineScale: Free Lunch in High-Resolution Cinematic Visual Generation · 5 authors 88 2
Submitted by alimotahharynia 11 DrugReasoner: Interpretable Drug Approval Prediction with a Reasoning-augmented Language Model · 6 authors 3 2
Submitted by taesiri 9 FastMesh:Efficient Artistic Mesh Generation via Component Decoupling · 5 authors 2
Submitted by liminghao1630 8 ReportBench: Evaluating Deep Research Agents via Academic Survey Tasks · 5 authors 13 2
Submitted by taesiri 6 ThinkDial: An Open Recipe for Controlling Reasoning Effort in Large Language Models · 5 authors 3
Submitted by Taishi-N324 6 Optimal Sparsity of Mixture-of-Experts Language Models for Reasoning Tasks · 7 authors 2
Submitted by HeBolei 5 Select to Know: An Internal-External Knowledge Self-Selection Framework for Domain-Specific Question Answering · 8 authors 2
Submitted by GuangcongWang 4 ObjFiller-3D: Consistent Multi-view 3D Inpainting via Video Diffusion Models · 7 authors 23 2
Submitted by lihaoxin2020 3 Demystifying Scientific Problem-Solving in LLMs by Probing Knowledge and Reasoning · 5 authors 2
Submitted by terryyz 3 Training Language Model Agents to Find Vulnerabilities with CTF-Dojo · 5 authors 2
Submitted by NicoleCho 2 QueryBandits for Hallucination Mitigation: Exploiting Semantic Features for No-Regret Rewriting · 5 authors 2
Submitted by dnoever 1 Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills · 1 authors 1
Submitted by KBhandari11 1 Unraveling the cognitive patterns of Large Language Models through module communities · 3 authors 2
Submitted by bigorange111 1 Steering When Necessary: Flexible Steering Large Language Models with Backtracking · 8 authors 0 2
Submitted by kubamc23 - Forecasting Probability Distributions of Financial Returns with Deep Neural Networks · 1 authors 1 2
Submitted by xavier-hu - ClaimGen-CN: A Large-scale Chinese Dataset for Legal Claim Generation · 9 authors 2