JS
Jinwoo Shin
cs.LGcs.AIcs.CVstat.MLcs.CLcs.ROcs.NIcs.DSmath.PRcs.CR
On Valency
published · living versionsW_vx5uxg54·v1 · currentpublished
Latent Reasoning in Continuous Space for Unified Multimodal Models
with Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee, Minsu Cho
1 version
W_wjv75535·v2published
W_cy2bmu9n·v1published
Preprints & journals
222 papers in the corpus · 2009–2026RLHND: Video Foundation Models as Physically Grounded Hand Trackers for Robot Learning2610.09455v1 · Seungjun Moon, Subin Jeon, Sangwoo Kim et al.2026 · 0 citationsarXiv
Q-Learning with Scalar Adjoint Matching2610.10437v1 · Yonghoon Dong, Minsung Yoon, Jaehyuk Kim et al.2026 · 0 citationsarXiv
PointWAM: 3D World Action Modeling for Dexterous Robotic Manipulation2610.02840v1 · Chunghyun Park, Beomjun Kim, Seungcheol Park et al.2026 · 0 citationsarXiv
Representation-Aligned Auxiliary Supervision for Language Model Adaptation2610.04098v2 · Kyuyoung Kim, Peiyao Sheng, Ashwin Hebbar et al.2026 · 0 citationsarXiv
Pose6DAug: Physically Plausible Multi-view Object Swapping for Robot Data Augmentation2606.20118v2 · Jonghoon Lee, Seong Hyeon Park, Byungwoo Jeon et al.2026 · 0 citationsarXiv
Naive Visual Memory is Not Enough: A Failure-Mode Study of GUI Agents2606.14106v1 · Seoyoung Choi, Minseok Ko, Hyunseok Lee et al.2026 · 0 citationsarXiv
Dexterous Point Policy: Learning Point-based Dexterous Hand Policies from Human Demonstrations2606.10614v1 · Beomjun Kim, Seong Hyeon Park, Seunghoon Sim et al.2026 · 0 citationsarXiv
SSAFE: Simple and Strong AI-Generated Image Detection via Frozen Vision Encoders2606.08634v1 · Seunghyun Lee, Byoungkwon Kim, Jaehyun Nam et al.2026 · 0 citationsarXiv
Benchmarking Visual State Tracking in Multimodal Video Understanding2606.03920v1 · Sihyun Yu, Nanye Ma, Pinzhi Huang et al.2026 · 0 citationsarXiv
Trust Region Q Adjoint Matching2605.27079v2 · Yonghoon Dong, Kyungmin Lee, Changyeon Kim et al.2026 · 0 citationsarXiv
ExComm: Exploration-Stage Communication for Error-Resilient Agentic Test-Time Scaling2605.22102v1 · Woomin Song, Beomjun Kim, Daewon Choi et al.2026 · 0 citationsarXiv
IdleSpec: Exploiting Idle Time via Speculative Planning for LLM Agents2605.22154v1 · Daewon Choi, Kyunghyun Park, Woomin Song et al.2026 · 0 citationsarXiv
Restoration-Aligned Generative Flow Models for Blind Motion Deblurring2605.08854v1 · Insoo Kim, Jinwoo Shin2026 · 0 citationsarXiv
RLDX-1 Technical Report2605.03269v2 · Dongyoung Kim, Huiwon Jang, Myungkyu Koo et al.2026 · 0 citationsarXiv
Modular Sensory Stream for Integrating Physical Feedback in Vision-Language-Action Models2604.23272v2 · Jimin Lee, Huiwon Jang, Myungkyu Koo et al.2026 · 0 citationsarXiv
Correct Answers from Sound Reasoning: Verifiable Process Supervision for Language Models2605.12519v2 · Kyuyoung Kim, Kevin Wang, Yunfei Xie et al.2026 · 0 citationsarXiv
Cog3DMap: Multi-View Vision-Language Reasoning with 3D Cognitive Maps2603.23023v1 · Chanyoung Gwak, Yoonwoo Jeong, Byungwoo Jeon et al.2026 · 0 citationsarXiv
SpatialBoost: Enhancing Visual Representation through Language-Guided Reasoning2603.22057v1 · Byungwoo Jeon, Dongyoung Kim, Huiwon Jang et al.2026 · 0 citationsarXiv
RoboAlign: Learning Test-Time Reasoning for Language-Action Alignment in Vision-Language-Action Models2603.21341v1 · Dongyoung Kim, Sumin Park, Woomin Song et al.2026 · 0 citationsarXiv
RedacBench: Can AI Erase Your Secrets?2603.20208v1 · Hyunjun Jeon, Kyuyoung Kim, Jinwoo Shin2026 · 0 citationsarXiv
RoboCurate: Harnessing Diversity with Action-Verified Neural Trajectory for Robot Learning2602.18742v1 · Seungku Kim, Suhyeok Jang, Byungjun Yoon et al.2026 · 0 citationsarXiv
Beyond Correctness: Learning Robust Reasoning via Transfer2602.08489v1 · Hyunseok Lee, Soheil Abbasloo, Jihoon Tack et al.2026 · 0 citationsarXiv
Vision-aligned Latent Reasoning for Multi-modal Large Language Model2602.04476v2 · Byungwoo Jeon, Yoonwoo Jeong, Hyunseok Lee et al.2026 · 0 citationsarXiv
Rethinking Prompt Design for Inference-time Scaling in Text-to-Visual Generation2512.03534v1 · Subin Kim, Sangwoo Mo, Mamshad Nayeem Rizve et al.2025 · 0 citationsarXiv
Hierarchical Vision Language Action Model Using Success and Failure Demonstrations2512.03913v1 · Jeongeun Park, Jihwan Yoon, Byungwoo Jeon et al.2025 · 0 citationsarXiv
Dual-Stream Diffusion for World-Model Augmented Vision-Language-Action Model2510.27607v3 · John Won, Kyungmin Lee, Huiwon Jang et al.2025 · 0 citationsarXiv
Decoupled MeanFlow: Turning Flow Models into Flow Maps for Accelerated Sampling2510.24474v1 · Kyungmin Lee, Sihyun Yu, Jinwoo Shin2025 · 0 citationsarXiv
A Definition of AGI2510.18212v3 · Dan Hendrycks, Dawn Song, Christian Szegedy et al.2025 · 3 citationsarXiv
Verifier-free Test-Time Sampling for Vision-Language-Action Models2510.05681v2 · Suhyeok Jang, Dongyoung Kim, Changyeon Kim et al.2025 · 0 citationsarXiv
ContextVLA: Vision-Language-Action Model with Amortized Multi-Frame Context2510.04246v1 · Huiwon Jang, Sihyun Yu, Heeseung Kwon et al.2025 · 0 citationsarXiv
Contrastive Representation Regularization for Vision-Language-Action Models2510.01711v4 · Taeyoung Kim, Jimin Lee, Myungkyu Koo et al.2025 · 0 citationsarXiv
HAMLET: Switch your Vision-Language-Action Model into a History-Aware Policy2510.00695v3 · Myungkyu Koo, Daewon Choi, Taeyoung Kim et al.2025 · 0 citationsarXiv
Scalable and Robust LLM Unlearning by Correcting Responses with Retrieved Exclusions2509.25973v1 · Junbeom Kim, Kyuyoung Kim, Jihoon Tack et al.2025 · 0 citationsarXiv
DS-STAR: Data Science Agent for Solving Diverse Tasks across Heterogeneous Formats and Open-Ended Queries2509.21825v4 · Jaehyun Nam, Jinsung Yoon, Jiefeng Chen et al.2025 · 2 citationsarXiv
Training Text-to-Molecule Models with Context-Aware Tokenization2509.04476v2 · Seojin Kim, Hyeontae Song, Jaehyun Nam et al.2025 · 0 citationsarXiv
Think Clearly: Improving Reasoning via Redundant Token Pruning2507.08806v1 · Daewon Choi, Jimin Lee, Jihoon Tack et al.2025 · 0 citationsarXiv
Efficient LLM Collaboration via Planning2506.11578v5 · Byeongchan Lee, Jonghoon Lee, Dongyoung Kim et al.2025 · 0 citationsarXiv
CLIP Meets Diffusion: A Synergistic Approach to Anomaly Detection2506.11772v3 · Byeongchan Lee, John Won, Seunghyun Lee et al.2025 · 0 citationsarXiv
Improving Motion in Image-to-Video Models via Adaptive Low-Pass Guidance2506.08456v2 · June Suk Choi, Kyungmin Lee, Sihyun Yu et al.2025 · 0 citationsarXiv
FontAdapter: Instant Font Adaptation in Visual Text Generation2506.05843v1 · Myungkyu Koo, Subin Kim, Sangkyung Kwak et al.2025 · 0 citationsarXiv
Debiasing Online Preference Learning via Preference Feature Preservation2506.11098v1 · Dongyoung Kim, Jinsung Yoon, Jinwoo Shin et al.2025 · 0 citationsarXiv
Accelerated Test-Time Scaling with Model-Free Speculative Sampling2506.04708v3 · Woomin Song, Saket Dingliwal, Sai Muralidhar Jayanthi et al.2025 · 0 citationsarXiv
Self-Refining Language Model Anonymizers via Adversarial Distillation2506.01420v2 · Kyuyoung Kim, Hyunjun Jeon, Jinwoo Shin2025 · 1 citationarXiv
Mamba Drafters for Speculative Decoding2506.01206v1 · Daewon Choi, Seunghyuk Oh, Saket Dingliwal et al.2025 · 1 citationarXiv
Compress, Gather, and Recompute: REFORMing Long-Context Processing in Transformers2506.01215v2 · Woomin Song, Sai Muralidhar Jayanthi, Srikanth Ronanki et al.2025 · 0 citationsarXiv
Robot-R1: Reinforcement Learning for Enhanced Embodied Reasoning in Robotics2506.00070v3 · Dongyoung Kim, Sumin Park, Huiwon Jang et al.2025 · 0 citationsarXiv
Sparsified State-Space Models are Efficient Highway Networks2505.20698v1 · Woomin Song, Jihoon Tack, Sangwoo Mo et al.2025 · 0 citationsarXiv
MLE-STAR: Machine Learning Engineering Agent via Search and Targeted Refinement2506.15692v3 · Jaehyun Nam, Jinsung Yoon, Jiefeng Chen et al.2025 · 1 citationarXiv
Test-Time Adaptation with Binary Feedback2505.18514v1 · Taeckyung Lee, Sorn Chottananurak, Junsu Kim et al.2025 · 1 citationarXiv
ReGUIDE: Data Efficient GUI Grounding via Spatial Reasoning and Search2505.15259v2 · Hyunseok Lee, Jeonghoon Kim, Beomjun Kim et al.2025 · 0 citationsarXiv
Career total: 360 works. 222 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.