1 citations · 1 across the 14 of their papers we have counts for
16 papers
On the average-case complexity landscape for Tensor-Isomorphism-complete problems over finite fields
Tiange Li, Yinan Li, Youming Qiao +2
In Grochow and Qiao (SIAM J. Comput., 2021), the complexity class Tensor Isomorphism (TI) was introduced and isomorphism problems for groups, algebras, and polynomials were shown t…
BadCLIP++: Stealthy and Persistent Backdoors in Multimodal Contrastive Learning
Siyuan Liang, Yongcheng Jing, Yingjie Wang +3
Research on backdoor attacks against multimodal contrastive learning models faces two key challenges: stealthiness and persistence. Existing methods often fail under strong detecti…
Why Self-Rewarding Works: Theoretical Guarantees for Iterative Alignment of Language Models
Shi Fu, Yingjie Wang, Shengchao Hu +2
Self-Rewarding Language Models (SRLMs) achieve notable success in iteratively improving alignment without external feedback. Yet, despite their striking empirical progress, the cor…
MedCoG: Maximizing LLM Inference Density in Medical Reasoning via Meta-Cognitive Regulation
Yu Zhao, Hao Guan, Yongcheng Jing +2
Large Language Models (LLMs) have shown strong potential in complex medical reasoning yet face diminishing gains under inference scaling laws. While existing studies augment LLMs w…
Disentangled Representation Learning via Flow Matching
Jinjin Chi, Taoping Liu, Mengtao Yin +5
Disentangled representation learning aims to capture the underlying explanatory factors of observed data, enabling a principled understanding of the data-generating process. Recent…
EchoBench: Benchmarking Sycophancy in Medical Large Vision-Language Models
Botai Yuan, Yutian Zhou, Yingjie Wang +9
Recent benchmarks for medical Large Vision-Language Models (LVLMs) emphasize leaderboard accuracy, overlooking reliability and safety. We study sycophancy -- models' tendency to un…
CoVeR: Conformal Calibration for Versatile and Reliable Autoregressive Next-Token Prediction
Yuzhu Chen, Yingjie Wang, Shunyu Liu +2
Autoregressive pre-trained models combined with decoding methods have achieved impressive performance on complex reasoning tasks. While mainstream decoding strategies such as beam…
Benchmarking Reasoning Robustness in Large Language Models
Tong Yu, Yongcheng Jing, Xikun Zhang +6
Despite the recent success of large language models (LLMs) in reasoning such as DeepSeek, we for the first time identify a key dilemma in reasoning robustness and generalization: s…
Graph-Augmented Reasoning: Evolving Step-by-Step Knowledge Graph Retrieval for LLM Reasoning
Wenjie Wu, Yongcheng Jing, Yingjie Wang +2
Recent large language model (LLM) reasoning, despite its success, suffers from limited domain knowledge, susceptibility to hallucinations, and constrained reasoning depth, particul…
Dynamic Parallel Tree Search for Efficient LLM Reasoning
Yifu Ding, Wentao Jiang, Shunyu Liu +9
Tree of Thoughts (ToT) enhances Large Language Model (LLM) reasoning by structuring problem-solving as a spanning tree. However, recent methods focus on search accuracy while overl…
A Theoretical Perspective: How to Prevent Model Collapse in Self-consuming Training Loops
Shi Fu, Yingjie Wang, Yuzhu Chen +2
High-quality data is essential for training large generative models, yet the vast reservoir of real data available online has become nearly depleted. Consequently, models increasin…
Reasoning with Reinforced Functional Token Tuning
Kongcheng Zhang, Qi Yao, Baisheng Lai +5
In this work, we propose Reinforced Functional Token Tuning (RFTT), a novel reinforced fine-tuning framework that empowers Large Language Models (LLMs) with self-play learn-to-reas…
Erasing Without Remembering: Implicit Knowledge Forgetting in Large Language Models
Huazheng Wang, Yongcheng Jing, Haifeng Sun +4
In this paper, we investigate knowledge forgetting in large language models with a focus on its generalisation, ensuring that models forget not only specific training samples but a…
HRP: High-Rank Preheating for Superior LoRA Initialization
Yuzhu Chen, Yingjie Wang, Shi Fu +4
This paper studies the crucial impact of initialization in Low-Rank Adaptation (LoRA). Through theoretical analysis, we demonstrate that the fine-tuned result of LoRA is highly sen…
Mulberry: Empowering MLLM with o1-like Reasoning and Reflection via Collective Monte Carlo Tree Search
Huanjin Yao, Jiaxing Huang, Wenhao Wu +8
In this work, we aim to develop an MLLM that understands and solves questions by learning to create each intermediate step of the reasoning involved till the final answer. To this…
A Theoretical Survey on Foundation Models
Shi Fu, Yuzhu Chen, Yingjie Wang +1
Understanding the inner mechanisms of black-box foundation models (FMs) is essential yet challenging in artificial intelligence and its applications. Over the last decade, the long…