Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs?

Shuibai Zhang*, Junhyuck Kim*, Gyeongman Kim, Jaewoong Cho

Language Model NeurIPS 2026

Is the Importance Ratio Necessary for Stable Reinforcement Learning in LLMs?

Pruning and Distilling Mixture-of-Experts into Dense Language Models

Junhyuck Kim, Jihun Yun, Haechan Kim, Gyeongman Kim, Joonghyun Bae, Jaewoong Cho

Language Model NeurIPS 2026 Oral

Pruning and Distilling Mixture-of-Experts into Dense Language Models

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

Haechan Kim, Yoonho Lee, Gisang Lee, Chelsea Finn, and Kangwook Lee

Language Model arXiv

WHALE: A Simple Recipe for Joint Harness-Weight Optimization

Multi-Bin Batching for Increasing LLM Inference Throughput

Ozgur Guldogan, Jackson Kunde, Kangwook Lee, and Ramtin Pedarsani

Language Model TOMPECS 2026

Multi-Bin Batching for Increasing LLM Inference Throughput

3D HAMSTER: Enabling Robust Manipulation in Hierarchical Vision Language Action Models through 3D Trajectory Guidance

Dongyoon Hwang*, Byung Kun Lee*, Dongjin Kim*, Hyojin Jang, Hoiyeong Jin, Jueun Mun, Minho Park, Hojoon Lee, Hyunseung Kim, Jaegul Choo

Language Model IROS 2026

3D HAMSTER: Enabling Robust Manipulation in Hierarchical Vision Language Action Models through 3D Trajectory Guidance

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

Ying Fan, Anej Svete, and Kangwook Lee

Language Model arXiv

Bridging the Gap Between Latent and Explicit Reasoning with Looped Transformers

AsyncOPD: How Stale Can On-Policy Distillation Be?

Wonjun Kang, Kevin Galim, Seunghyuk Oh, Minjun Kang, Sanghyun Park, Donghoon Kim, Minjae Lee, Minseo Kim, Rishabh Tiwari, Yuchen Zeng, Hyung Il Koo, Kangwook Lee

Language Model ICML 2026 Workshop

AsyncOPD: How Stale Can On-Policy Distillation Be?

AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents

Seoyeon An*, Hyeonseo Jang*, Minsu Kim*, Chanho Lee, Younghan Park, Kangwook Lee

Language Model ICML 2026 Workshop

AgentVidBench: A Multi-Hop Video Question Answering Benchmark for Evaluating MLLM Agents

Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents

Hyogon Ryu, Jeonghwan Kim, Yewon Lim, Chaeun Lee, Jeongwook Kim, Donghoon Ham

Language Model ICML 2026 Workshop

Online Agent-as-a-Judge: Situation-Generating Evaluation for Interactive Agents

Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling

Seojeong Park*, Jiho Choi*, Junyong Kang, Seonho Lee, Jaeyo Shin, Hyunjung Shim

Language Model ICML 2026 Workshop

Mitigating Perceptual Judgment Bias in Multimodal LLM-as-a-Judge via Perceptual Perturbation and Reward Modeling