University of Southern California · 25 records

dateidtitleauthorsvenue↑
2026-11-182611.22275Heave-Ho: Decentralized Long-Horizon Multi-Humanoid CollaborationTing-Hsuan Chen et al.arXiv21
2026-11-172611.20385DominoBench: Evaluating Multi-Step Physical Reasoning from Still ImagesEmilio FerraraarXiv6
2026-11-06W4415169768Hippocampal transformations occur along dimensions of memory interferenceSoroush Mirjalili et al.Nature Communications
2026-11-042611.04166Say the Same, Act Differently: Diagnosing and Steering Text-Action Divergence in Reasoning VLAsZihao Feng et al.arXiv
2026-10-232610.30418Agent Mosaic: Recognizing Confidentiality Leaks in Agentic LLM SystemsDaniel Ruiz et al.arXiv24
2026-10-202610.25265SPARC: Spoken Profile Authorship Recognition CorpusEfthymios Tsaprazlis et al.arXiv4
2026-10-162610.223413DCodeVerse: Exploring 3D Worlds as CodeYipeng Gao et al.arXiv62
2026-10-152610.17301The Agent Knew: Internal States Forecast Unauthorized Actions and Stop Them, and the Lies That FollowArya Fayyazi et al.arXiv4
2026-10-14W4388032289Learning Optimal Classification Trees Robust to Distribution ShiftsNathan Justin et al.Operations Research
2026-10-13W4415878239Constrained bilinear optimal control of reactive evolution equationsZhexian Li et al.International Journal of Heat and Mass Transfer
2026-10-122610.07121SoloQ: Calibration-Free Quantization for Diffusion Language ModelsDonghyun Lee et al.arXiv30
2026-10-062610.02586Labels Override Definitions in Jev-Style Typed Decision ModelsSeyedarmin Azizi et al.arXiv4
2026-10-062610.06804Sharpen Without Search: On-Policy Distillation of Sequence-Level Power DistributionErfan Baghaei Potraghloo et al.arXiv3
2026-10-022609.32259Prefill-Free Cross-Family KV Cache Transfer for Heterogeneous Multi-Agent LLMsVincent-Daniel Yun et al.arXiv26
2026-09-252609.30077Rate-distortion optimization for full-reference image quality metrics via stochastic Hessian estimatesSamuel Fernández-Menduiña et al.arXiv5
2026-09-092608.29109Recognition-Refusal Misalignment in LLMs: Why Models Answer Structurally Unanswerable QuestionsYucheng Du et al.arXiv2
2026-07-232607.16165An Exam for Active ObserversJiarui Zhang et al.arXiv26
2026-07-212607.17524Token-Level Off-Policy Learning for Faithful Generation Under Distribution ShiftZitong Huang et al.arXiv6
2026-07-132607.07964KronQ: LLM Quantization via Kronecker-Factored HessianDonghyun Lee et al.arXiv27
2026-06-152606.14240AFFORDANCE20Q: Evaluating Affordance Reasoning from Physical PropertiesYifan Jiang et al.arXiv3
2026-06-082606.05152Reinforcement Learning from Rich Feedback with Distributional DAggerRishabh Agrawal et al.arXiv4
2026-06-032606.03928Value-Aware Stochastic KV Cache Eviction for Reasoning ModelsTing-Yun Chang et al.arXiv5
2026-05-292605.29257ChildVox: A Speech, Audio, and Large Audio-Language Model Benchmark in Understanding and Characterizing Sound across ChildhoodTiantian Feng et al.arXiv5
2026-05-132605.12466Solve the Loop: Attractor Models for Language and ReasoningJacob Fein-Ashley et al.arXiv5
2026-05-112605.06241Rethinking RL for LLM Reasoning: It's Sparse Policy Selection, Not Capability LearningÖmer Faruk Akgül et al.arXiv4