…Website and code: https://prpl-group.com/kinder-site/ View arXiv page View PDF Project page GitHub 30 Add to collection Community KinDER is a stress test for Kinematic and Dynamic Embodied…
…with agentic tool use, it yields a 24\% relative gain in pass@1. Attention analysis shows that FocuSFT reduces attention sink mass by 529times and triples context engagement during training. Code: https…
…https://arxiv.org/abs/2605.12484 Code: http://rishabhtiwari.ai/projects/fst/code This comment has been hidden Get this paper in your agent: hf papers read 2605.12484 Don't have…
…We release our code and dataset to facilitate future research on patent examination modeling. View arXiv page View PDF Project page GitHub 8 Add to collection Community PatRe is the first benchmark…
…Who Guards the Benchmarks? Automated Auditing of LLM Agent Benchmarks (2026) AuditRepairBench: A Paired-Execution Trace Corpus for Evaluator-Channel Ranking Instability in Agent Repair (2026) ValueBlindBench: Agreement-Gated Stress Testing of…
…We make our code and data available at: https://github.com/cisnlp/COPSD. View arXiv page View PDF GitHub 3 Add to collection Community Get this paper in your agent: hf papers…
…Our code is available at https://github.com/dmksjfl/DR.Q. View arXiv page View PDF GitHub 10 Add to collection Community ICML2026 Get this paper in your agent: hf papers read…
…View arXiv page View PDF Add to collection Community EverAnimate code, 480p LoRA checkpoints, minimal demo data, and training/inference scripts are now released: https://huggingface.co/epfl-vita/everanimate Resources: Code…
…on real hardware compared with dense inference. Codes and checkpoints are all available at https://github.com/thunlp/DECO . Get this paper in your agent: hf papers read 2605.10933 Don't…
…AI-generated summary Reinforcement learning with verifiable rewards (RLVR) has become a central paradigm for improving reasoning and code generation in large language models, and GRPO-style training is widely adopted for…