127 citations · 512 across the 55 of their papers we have counts for
12 papers · 1 filter
Why, Where, How: Taxonomy-guided Error Grounding for Code Repair in NL2SQL
Suchan Lee, Woomin Song, Hwanjo Yu +1
SQL queries that large language models write from natural language questions can execute successfully yet produce incorrect results, so execution alone does not reveal what to fix.…
Difficulty-Adaptive Tree-Structured Policy Optimization for Expanding Reasoning Coverage in RLVR
Youngjun Yu, Sanghwan Jang, Hwanjo Yu
Reinforcement Learning with Verifiable Rewards (RLVR) has been central to the recent success of Large Reasoning Models. However, while RLVR significantly improves single-sample acc…
Personalized and Multi-View Representation for Federated Cold-Start Recommendation
Jaehyung Lim, Wonbin Kweon, Woojoo Kim +3
Federated recommendation (FedRec) enables personalized modeling without centralizing users' interaction histories, but most existing methods assume a fixed item pool and thus overl…
RA-VLA: Retrieval-Augmented VLA for Test-Time Adaptation
Sanghwan Jang, Minjin Jeon, Minsoo Kim +3
Vision-Language-Action (VLA) models provide a versatile foundation for general robotic manipulation, yet they exhibit significant brittleness when confronted with novel task distri…
TRACER: Balancing Stability-Plasticity-Cognitivity Trilemma for LLM Enhanced Continual Recommendation
WooJoo Kim, HyunSik Yoo, JunYoung Kim +3
Continual recommendation aims to capture evolving user interests from streaming data but struggles with sparsity. LLM enhancers mitigate this with semantic knowledge, but naive int…
GOD: Enhancing Generalization via Deep Grafting for Sequential Recommendation
WooJoo Kim, JunYoung Kim, JaeHyung Lim +1
Sequential recommenders often struggle with sparse and noisy histories, limiting generalization to unseen interactions. Knowledge distillation mitigates this by transferring dense…
ReWEIGH the Evidence: Calibrating Token-Level Ordinal Visual Evidence to Mitigate Hallucinations in Large Vision-Language Models
Jihae Jeong, Junha Choi, Hwanjo Yu
Large vision-language models (LVLMs) often hallucinate, generating content that the input image does not support. Preventing such content during decoding calls for a candidate-spec…
From Overlooked to Explored: Recovering Item Relations via Mixture of Perspectives for Sequential Recommendation
Junyoung Kim, Wonbin Kweon, Woojoo Kim +3
Capturing user preference from a user's interaction sequence is the central challenge of Sequential Recommendation (SR). This preference intuitively emerges from inter-item relatio…
Valid Necessary: Diagnosing Latent Inefficiency in Chain-of-Thought
Daeyeop Lee, Hwanjo Yu
Chain-of-Thought (CoT) prompting has significantly advanced the reasoning capabilities of Large Language Models (LLMs), yet it often incurs substantial computational costs due to o…
FLAME: Condensing Ensemble Diversity into a Single Network for Efficient Sequential Recommendation
WooJoo Kim, JunYoung Kim, JaeHyung Lim +3
Sequential recommendation requires capturing diverse user behaviors, which a single network often fails to capture. While ensemble methods mitigate this, training multiple networks…
VLM2Rec: Resolving Modality Collapse in Vision-Language Model Embedders for Multimodal Sequential Recommendation
Junyoung Kim, Woojoo Kim, Wonbin Kweon +3
Sequential Recommendation (SR) in multimodal settings typically relies on small frozen pretrained encoders, which limits semantic capacity and prevents Collaborative Filtering (CF)…
Improving Scientific Document Retrieval with Academic Concept Index
Jeyun Lee, Junhyoung Lee, Wonbin Kweon +7
Adapting general-domain retrievers to scientific domains is challenging due to the scarcity of large-scale domain-specific relevance annotations and the substantial mismatch in voc…