9 papers
Reward-Tilted On-Policy Distillation for Acoustic Grounding in Audio-Language Models
Kaiyang Li, Shaobo Han, Yue Tian +1
Audio-language models (ALMs) can exploit textual shortcuts to answer questions while overlooking acoustic evidence, weakening audio understanding. On-policy distillation (OPD) trai…
Mizar: A 159M-Parameter Audio-Language Model for Audio Understanding
Kaiyang Li, Shaobo Han, Yue Tian +1
Audio-language models (ALMs) integrate acoustic perception with the knowledge encoded in language models, enabling contextual understanding of auditory events. Making these capabil…
Toward Open-World Video Segmentation over Long Horizons
Qing Su, Kaiyang Li, Yuan Zhuang +2
Long videos challenge open-world segmentation systems to continually discover objects and preserve their identities through disappearance and reappearance. Savvy, a zero-shot, semi…
ReForge: Refining Merged Models with Anchor-Regularized Regression
Kaiyang Li, Shaobo Han, Qing Su +1
Model merging aims to combine multiple task-specific expert models into a single model without joint retraining, offering a practical alternative to multi-task learning when data a…
Low-Rank Adaptation for Critic Learning in Off-Policy Reinforcement Learning
Yuan Zhuang, Yuexin Bian, Sihong He +7
Scaling critic capacity is a promising direction for improving off-policy reinforcement learning (RL). However, recent work shows that larger critics are prone to overfitting and i…
Approximate Subgraph Matching with Neural Graph Representations and Reinforcement Learning
Kaiyang Li, Shihao Ji, Zhipeng Cai +1
Approximate subgraph matching (ASM) is a task that determines the approximate presence of a given query graph in a large target graph. Being an NP-hard problem, ASM is critical in…
LD-MoLE: Learnable Dynamic Routing for Mixture of LoRA Experts
Yuan Zhuang, Yi Shen, Yuexin Bian +4
Recent studies have shown that combining parameter-efficient fine-tuning (PEFT) with mixture-of-experts (MoE) is an effective strategy for adapting large language models (LLMs) to…
Uni-LoRA: One Vector is All You Need
Kaiyang Li, Shaobo Han, Qing Su +3
Low-Rank Adaptation (LoRA) has become the de facto parameter-efficient fine-tuning (PEFT) method for large language models (LLMs) by constraining weight updates to low-rank matrice…
Unsqueeze [CLS] Bottleneck to Learn Rich Representations
Qing Su, Shihao Ji
Distillation-based self-supervised learning typically leads to more compressed representations due to its radical clustering process and the implementation of a sharper target dist…