1 citations · 1 across the 17 of their papers we have counts for
19 papers
KV4-RL: Unlocking Faster Asynchronous Rollouts for RLVR with INT4 KV Cache Quantization
Sihwan Park, Sung-Yub Kim, Doohyuk Jang +1
Asynchronous rollout improves the efficiency of reinforcement learning with verifiable rewards (RLVR) by reducing under-utilization during long-tail generation. Sustained concurren…
Learning Beyond What You Sample: Off-Policy-Aware Cross-Model Trajectory Exchange for RLVR
Doohyuk Jang, Yoonsik Park, Gyouk Chu +2
Reinforcement Learning with Verifiable Rewards (RLVR) methods such as GRPO rely on successful self-generated trajectories, but finite rollout budgets can produce all-fail groups wi…
J-Zero: Unified Challenger--Solver--Judge Self-Evolution from Zero Data
Gyouk Chu, Myeongho Jeon, Eunho Yang +1
Self-evolving language models have recently emerged as a promising path toward superintelligence, with the advantage of reducing the cost of human supervision. While considerable p…
CollabVR: Collaborative Video Reasoning with Vision-Language and Video Generation Models
Joowon Kim, Seungho Shin, Joonhyung Park +1
Recent "Thinking with Video" approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reasoning artifacts. Even strong…
Integrating Multimodal Large Language Model Knowledge into Amodal Completion
Heecheol Yun, Eunho Yang
With the widespread adoption of autonomous vehicles and robotics, amodal completion, which reconstructs the occluded parts of people and objects in an image, has become increasingl…
Discounted Beta-Bernoulli Reward Estimation for Sample-Efficient Reinforcement Learning with Verifiable Rewards
Haechan Kim, Soohyun Ryu, Gyouk Chu +2
Reinforcement learning with verifiable rewards (RLVR) has emerged as an effective post-training paradigm for improving the reasoning capabilities of large language models. However,…
Argument Reconstruction as Supervision for Critical Thinking in LLMs
Hyun Ryu, Gyouk Chu, Gregor Betz +3
To think critically about arguments, human learners are trained to identify, reconstruct, and evaluate arguments. Argument reconstruction is especially important because it makes a…
Accelerating Vision Transformers with Adaptive Patch Sizes
Rohan Choudhury, JungEun Kim, Jinhyung Park +3
Vision Transformers (ViTs) partition input images into uniformly sized patches regardless of their content, resulting in long input sequence lengths for high-resolution images. We…
When to Ensemble: Identifying Token-Level Points for Stable and Fast LLM Ensembling
Heecheol Yun, Kwangmin Ki, Junghyun Lee +1
Ensembling Large Language Models (LLMs) has gained attention as a promising approach to surpass the performance of individual models by leveraging their complementary strengths. In…
Verifying Meta-Awareness via Predictive Rewards in Reasoning Models
Yoonjeon Kim, Doohyuk Jang, Eunho Yang
Recent research on reasoning models explores the meta-awareness of language models, including their ability to determine optimal thinking duration, recognize knowledge boundaries,…
No Prompt Left Behind: Exploiting Zero-Variance Prompts in LLM Reinforcement Learning via Entropy-Guided Advantage Shaping
Thanh-Long V. Le, Myeongho Jeon, Kim Vu +2
Reinforcement Learning with Verifiable Rewards (RLVR) is a powerful framework for improving the reasoning abilities of Large Language Models (LLMs). However, current methods such a…
ReviewScore: Misinformed Peer Review Detection with Large Language Models
Hyun Ryu, Doohyuk Jang, Hyemin S. Lee +16
Peer review serves as a backbone of academic research, but in most AI conferences, the review quality is degrading as the number of submissions explodes. To reliably detect low-qua…
Reasoning Model is Stubborn: Diagnosing Instruction Overriding in Reasoning Models
Doohyuk Jang, Yoonjeon Kim, Chanjae Park +2
Large language models have demonstrated remarkable proficiency in long and complex reasoning tasks. However, they frequently exhibit a problematic reliance on familiar reasoning pa…
LANTERN++: Enhancing Relaxed Speculative Decoding with Static Tree Drafting for Visual Auto-regressive Models
Sihwan Park, Doohyuk Jang, Sungyub Kim +2
Speculative decoding has been widely used to accelerate auto-regressive (AR) text generation. However, its effectiveness for visual AR models remains limited due to token selection…
Every Expert Matters: Towards Effective Knowledge Distillation for Mixture-of-Experts Language Models
Gyeongman Kim, Gyouk Chu, Eunho Yang
With the emergence of Mixture-of-Experts (MoE), the efficient scaling of model size has accelerated the development of large language models in recent years. However, their high me…
Med-PerSAM: One-Shot Visual Prompt Tuning for Personalized Segment Anything Model in Medical Domain
Hangyul Yoon, Doohyuk Jang, Jungeun Kim +1
Leveraging pre-trained models with tailored prompts for in-context learning has proven highly effective in NLP tasks. Building on this success, recent studies have applied a simila…
Divide and Translate: Compositional First-Order Logic Translation and Verification for Complex Logical Reasoning
Hyun Ryu, Gyeongman Kim, Hyemin S. Lee +1
Complex logical reasoning tasks require a long sequence of reasoning, which a large language model (LLM) with chain-of-thought prompting still falls short. To alleviate this issue,…
LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
Doohyuk Jang, Sihwan Park, June Yong Yang +5
Auto-Regressive (AR) models have recently gained prominence in image generation, often matching or even surpassing the performance of diffusion models. However, one major limitatio…
PromptKD: Distilling Student-Friendly Knowledge for Generative Language Models via Prompt Tuning
Gyeongman Kim, Doohyuk Jang, Eunho Yang
Recent advancements in large language models (LLMs) have raised concerns about inference costs, increasing the need for research into model compression. While knowledge distillatio…