Seoul National University · 37 records

dateidtitleauthorsvenue↑
2026-11-192611.23808PReMind: When Personal Memory Meets Visual HazardsYeongtak Oh et al.arXiv9
2026-11-062611.02660HeLM: Hierarchical Explicit Language Memory for Non-Markovian ManipulationGyeonghun Kim et al.arXiv7
2026-11-052611.05304LoopVQ: Sub 1-bit KV Cache Quantization for Looped TransformersMinsoo Cheong et al.arXiv9
2026-11-02W7225036729Radial magnetic field component plays a key role in determining the plasma density peak location in magnetized capacitively coupled plasmasSang Yoel Park et al.Applied Physics Letters
2026-10-262610.34674Benchmarking Obstacle-Conditioned Safety in Household Robot NavigationHyunwoong Bae et al.arXiv11
2026-10-212610.23400On the Tip of the Tongue: First-Token Cueing as a Behavioral Probe of Recall Failures in LLMsJaewon Sok et al.arXiv7
2026-10-162610.19605PN-Mix: Pair-Norm Guided Mixed-Precision Key Cache Quantization for Efficient Long-Output LLM InferenceGil Jae Song et al.arXiv5
2026-10-152610.19121Unlocking Structured Pruning for Reasoning Language Models via Attention-Preserving MLP TrimmingWoosang Lim et al.arXiv6
2026-10-062610.03120In-Distribution Forcing for Long Video Generation at Test TimeJeongwoo Shin et al.arXiv45
2026-10-052610.00531Science or Slop?: Benchmarking and Mitigating Scientific Slop in AI-Generated PapersYerim Oh et al.arXiv32
2026-10-052610.03195Source Preference in the Wild: How LLM Agents Favor Items by Source, and How to Reduce ItJonghyun Song et al.arXiv26
2026-10-022609.39375Beyond the Current Scene: Event-Referential Grasping with Active View SelectionHyunjoon Lee et al.arXiv30
2026-09-302609.37441Anisotropic Representations Improve Planning in JEPA World ModelsMingu Kang et al.arXiv26
2026-09-292609.33378Recursive Harness Distillation across Agents for Robot ManipulationSeungyeon Kim et al.arXiv40
2026-09-282609.25716FoMo: Forking Moment in Generative Trajectory as a Perceptual DistanceJaihyun Lew et al.arXiv19
2026-09-032608.30949MULTI3IR: A Benchmark for Multi-perspective Multi-domain Multi-modal Information RetrievalSeokwon Song et al.arXiv10
2026-09-032609.00834Replacing Training with Memory: Listwise Selection for Text-to-SQLYeonseok Jeong et al.arXiv4
2026-09-012608.28600SHAPE of Chain-of-Thought in Math ReasoningJonghyun Song et al.arXiv27
2026-09-012608.30428Lies We Can See: Joint Verbal and Non-Verbal Deception by VLM Agents in Embodied Social InteractionsJaewoo Ahn et al.arXiv12
2026-08-122607.27749Articulated Object Reconstruction from Rest-State ObservationDaeun Lee et al.arXiv47
2026-07-142607.091254D Human-Scene Reconstruction from Low-Overlap CapturesMinhyuk Hwang et al.arXiv50
2026-07-022607.00666Domain Arithmetic: One-Shot VLA Adaptation under Environmental ShiftsTaewook Kang et al.arXiv23
2026-07-012606.29985Are We Measuring Strategy or Phrasing? The Gap Between Surface- and Approach-Level Diversity in LLM Math ReasoningSangmook Lee et al.arXiv11
2026-06-232606.21139PoLAR: Factorizing Extent and Mode in Latent Actions for Robot Policy LearningYoungjoon Jeong et al.arXiv13
2026-06-092509.10078Human Psychometric Questionnaires Mischaracterize LLM BehaviorWoojung Song et al.arXiv35
2026-06-092606.05011CIPER: A Unified Framework for Cross-view Image-retrieval and Pose-estimationYurim Jeon et al.arXiv
2026-06-052606.05553ArcANE: Do Role-Playing Language Agents Stay in Character at the Right Time?Woojung Song et al.arXiv49
2026-06-052606.03312RobotValues: Evaluating Household Robots When Human Values ConflictJongwook Han et al.arXiv18
2026-06-012605.29429One Click per Cell Type Suffices: Training-free Group Interaction for Cell Instance SegmentationSanghyun Jo et al.arXiv2
2026-06-012605.28181When Confidence Misleads: Suffix Anchoring and Anchor-Proximity Confidence Modulation for Diffusion Language ModelsJungwon Park et al.arXiv1
2026-05-282605.28003ResearchMath-14K: Scaling Research-Level Mathematics via AgentsGuijin Son et al.arXiv46
2026-05-252605.17448Self-Improving CAD Generation Agents with Finite Element Analysis as FeedbackGuijin Son et al.arXiv20
2026-05-222605.15669Rule2DRC: Benchmarking LLM Agents for DRC Script Synthesis with Execution-Guided Test GenerationJinuk Kim et al.arXiv7
2026-05-142605.07865KL for a KL: On-Policy Distillation with Control Variate BaselineMinjae Oh et al.arXiv8
2026-05-132605.07579Your Language Model is Its Own Critic: Reinforcement Learning with Value Estimation from Actor's Internal StatesYunho Choi et al.arXiv8
2026-05-122605.09996Omni-Persona: Systematic Benchmarking and Improving Omnimodal PersonalizationYeongtak Oh et al.arXiv6
2026-05-122605.05886Training-Free Dense Hand Contact Estimation with Multi-Modal Large Language ModelsDaniel Sungho Jung et al.arXiv1