4 papers
Action- and Language-Conditioned Video Assessment for Embodied Control
Hwanhee Kim, Jaehyun Jang, Seungmin Cha +3
Vision-based embodied agents executing multi-step natural language instructions require feedback mechanisms that assess task progress over complete trajectories. Conventional appro…
Token-level Response-visual Attention Guidance for Multimodal LLMs Knowledge Distillation
Jaehyun Jang, Eunseop Yoon, Hee Suk Yoon +3
While knowledge distillation (KD) is widely adopted for training lightweight models by leveraging supervision from larger teacher models, relying solely on output token distributio…
Decomposed On-Policy Distillation for Vision-Language Reasoning: Steering Gradients for Visual Grounding
Hee Suk Yoon, Eunseop Yoon, Jaehyun Jang +6
While on-policy distillation offers dense supervision for training small reasoning models, its optimization dynamics in the multimodal domain remain under-explored. In this work, w…
PACR: Progressively Ascending Confidence Reward for LLM Reasoning
Eunseop Yoon, Hee Suk Yoon, Jaehyun Jang +5
Reinforcement Learning with Verifiable Rewards (RLVR) has significantly improved LLM reasoning, but its sparse, outcome-based reward provides no guidance for intermediate steps, sl…