13 papers
PhyCritic: Multimodal Critic Models for Physical AI
Tianyi Xiong, Shihao Wang, Guilin Liu +5
With the rapid development of large multimodal models, reliable judge and critic models have become essential for open-ended evaluation and preference alignment, providing pairwise…
KV-CoRE: Benchmarking Data-Dependent Low-Rank Compressibility of KV-Caches in LLMs
Jian Chen, Zhuoran Wang, Jiayu Qin +6
Large language models rely on kv-caches to avoid redundant computation during autoregressive decoding, but as context length grows, reading and writing the cache can quickly satura…
PRISM: Parametrically Refactoring Inference for Speculative Sampling Draft Models
Xuliang Wang, Yuetao Chen, Maochan Zhen +5
Large Language Models (LLMs), constrained by their auto-regressive nature, suffer from slow decoding. Speculative decoding methods have emerged as a promising solution to accelerat…
Risk Awareness Injection: Calibrating Vision-Language Models for Safety without Compromising Utility
Mengxuan Wang, Yuxin Chen, Gang Xu +3
Vision language models (VLMs) extend the reasoning capabilities of large language models (LLMs) to cross-modal settings, yet remain highly vulnerable to multimodal jailbreak attack…
Learning to Decode Against Compositional Hallucination in Video Multimodal Large Language Models
Wenbin Xing, Quanxing Zha, Lizheng Zu +3
Current research on video hallucination mitigation primarily focuses on isolated error types, leaving compositional hallucinations, arising from incorrect reasoning over multiple i…
IIB-LPO: Latent Policy Optimization via Iterative Information Bottleneck
Huilin Deng, Hongchen Luo, Yue Zhu +8
Recent advances in Reinforcement Learning with Verifiable Rewards (RLVR) for Large Language Model (LLM) reasoning have been hindered by a persistent challenge: exploration collapse…
RoboTidy : A 3D Gaussian Splatting Household Tidying Benchmark for Embodied Navigation and Action
Xiaoquan Sun, Ruijian Zhang, Kang Pang +5
Household tidying is an important application area, yet current benchmarks neither model user preferences nor support mobility, and they generalize poorly, making it hard to compre…
RETuning: Upgrading Inference-Time Scaling for Stock Movement Prediction with Large Language Models
Xueyuan Lin, Cehao Yang, Ye Ma +7
Recently, large language models (LLMs) have demonstrated outstanding reasoning capabilities on mathematical and coding tasks. However, their application to financial tasks-especial…
A Unified LLM-Adaptable Framework for Cold-Start Cognitive Diagnosis
Zihan Yao, Chentao Song, Yu He +4
Cognitive Diagnosis has become a critical task in AI-empowered education, supporting personalized learning by accurately assessing students' cognitive states. However, traditional…
ResoFilter: Fine-grained Synthetic Data Filtering for Large Language Models through Data-Parameter Resonance Analysis
Zeao Tu, Xiangdi Meng, Yu He +4
Large language models (LLMs) have shown remarkable effectiveness across various domains, with data augmentation methods utilizing GPT for synthetic data generation becoming prevale…
MARM: Unlocking the Future of Recommendation Systems through Memory Augmentation and Scalable Complexity
Xiao Lv, Jiangxia Cao, Shijie Guan +7
Scaling-law has guided the language model designing for past years, however, it is worth noting that the scaling laws of NLP cannot be directly applied to RecSys due to the followi…
Scaling Laws for Discriminative Classification in Large Language Models
Dean Wyatte, Fatemeh Tahmasbi, Ming Li +1
Modern large language models (LLMs) represent a paradigm shift in what can plausibly be expected of machine learning models. The fact that LLMs can effectively generate sensible an…
Scalable Model Editing via Customized Expert Networks
Zihan Yao, Yu He, Tianyu Qi +1
Addressing the issues of hallucinations and outdated knowledge in large language models is critical for their reliable application. Model Editing presents a promising avenue for mi…