1 citations · 1 across the 8 of their papers we have counts for
9 papers
Think, then Score: Decoupled Reasoning and Scoring for Video Reward Modeling
Yuan Wang, Ouxiang Li, Yulong Xu +8
Recent advances in generative video models are increasingly driven by post-training and test-time scaling, both of which critically depend on the quality of video reward models (RM…
RMBRec: Robust Multi-Behavior Recommendation towards Target Behaviors
Miaomiao Cai, Zhijie Zhang, Junfeng Fang +3
Multi-behavior recommendation faces a critical challenge in practice: auxiliary behaviors (e.g., clicks, carts) are often noisy, weakly correlated, or semantically misaligned with…
Bi-Mem: Bidirectional Construction of Hierarchical Memory for Personalized LLMs via Inductive-Reflective Agents
Wenyu Mao, Haosong Tan, Shuchang Liu +4
Constructing memory from users' long-term conversations overcomes LLMs' contextual limitations and enables personalized interactions. Recent studies focus on hierarchical memory to…
Thinking with Frames: Generative Video Distortion Evaluation via Frame Reward Model
Yuan Wang, Borui Liao, Huijuan Huang +5
Recent advances in video reward models and post-training strategies have improved text-to-video (T2V) generation. While these models typically assess visual quality, motion quality…
FACE: A General Framework for Mapping Collaborative Filtering Embeddings into LLM Tokens
Chao Wang, Yixin Song, Jinhui Ye +5
Recently, large language models (LLMs) have been explored for integration with collaborative filtering (CF)-based recommendation systems, which are crucial for personalizing user e…
AdaViP: Aligning Multi-modal LLMs via Adaptive Vision-enhanced Preference Optimization
Jinda Lu, Jinghan Li, Yuan Gao +4
Preference alignment through Direct Preference Optimization (DPO) has demonstrated significant effectiveness in aligning multimodal large language models (MLLMs) with human prefere…
Route Sparse Autoencoder to Interpret Large Language Models
Wei Shi, Sihang Li, Tao Liang +4
Mechanistic interpretability of large language models (LLMs) aims to uncover the internal processes of information propagation and reasoning. Sparse autoencoders (SAEs) have demons…
DAMA: Data- and Model-aware Alignment of Multi-modal LLMs
Jinda Lu, Junkang Wu, Jinghan Li +6
Direct Preference Optimization (DPO) has shown effectiveness in aligning multi-modal large language models (MLLM) with human preferences. However, existing methods exhibit an imbal…
Delayed Feedback Modeling with Influence Functions
Chenlu Ding, Jiancan Wu, Yancheng Yuan +5
In online advertising under the cost-per-conversion (CPA) model, accurate conversion rate (CVR) prediction is crucial. A major challenge is delayed feedback, where conversions may…