2 citations · 2 across the 19 of their papers we have counts for
22 papers
Can Test-Time Memory Evolution Outperform Test-Time Training for Scientific Discovery?
Yepeng Liu, Shengmai Chen, Xuandong Zhao +4
Recent \emph{test-time training} (TTT) frameworks have enabled open-weight large language models (LLMs) to outperform inference-only frameworks powered by frontier models on scient…
Learning to Follow In-Context Watermark Instructions via Self-Distillation
Yepeng Liu, Tianyi Chen, Xuandong Zhao +2
In-context watermarking (ICW) prepends an instruction to a query asking the model to embed a statistically detectable signal in its response. It thus equips LLMs with a watermarkin…
Rethinking AI-Generated Text Detection: A Strong Baseline and the Distribution-Shift Problem That Remains
Zhuoer Shen, Mingyi Wang, Shaofeng Zou +1
Recent AI-generated text detection work often introduces a new benchmark together with a specialized detector tailored to it. We revisit this practice from a baseline-first perspec…
WorldMemArena: Evaluating Multimodal Agent Memory Through Action-World Interaction
Chengzhi Liu, Yuzhe Yang, Sophia Xiao Pu +14
Multimodal large language models are increasingly deployed as long-horizon agents, where memory must do more than recall: it must track an evolving world, revise what has gone stal…
Detector-Evasive LLM Paraphrasing via Constrained Policy Optimization
Mingyi Wang, Zhuoer Shen, Yuheng Bu +1
AI-text detectors are vulnerable to paraphrasing and detector-guided paraphrasing attacks, but existing detector-evasion methods often lack precise control over semantic preservati…
Auditing Agent Harness Safety
Chengzhi Liu, Yichen Guo, Yepeng Liu +8
LLM agents increasingly run inside execution harnesses that dispatch tools, allocate resources, and route messages between specialized components. However, a harness can return a c…
Fundamental Trade-Offs in Multi-Bit Watermarking of Stochastic Processes
Haiyun He, Yepeng Liu, Zhuoer Shen +3
We study multi-bit watermarking for data generated by stochastic processes, where a hidden message is embedded during sampling and must be decodable by an authorized detector that…
Length Value Model: Scalable Value Pretraining for Token-Level Length Modeling
Zhen Zhang, Changyi Yang, Zijie Xia +11
Tokens are the fundamental units of computation in modern autoregressive models, and generation length directly influences both inference cost and reasoning performance. Despite it…
ConvexBench: Can LLMs Recognize Convex Functions?
Yepeng Liu, Yu Huang, Yu-Xiang Wang +2
Convex analysis is a modern branch of mathematics with many applications. As Large Language Models (LLMs) start to automate research-level math and sciences, it is important for LL…
A Reinforcement Learning Framework for Robust and Secure LLM Watermarking
Li An, Yujian Liu, Yepeng Liu +3
Watermarking has emerged as a promising solution for tracing and authenticating text generated by large language models (LLMs). A common approach to LLM watermarking is to construc…
Position: LLM Watermarking Should Align Stakeholders' Incentives for Practical Adoption
Yepeng Liu, Xuandong Zhao, Dawn Song +2
Despite progress in watermarking algorithms for large language models (LLMs), real-world deployment remains limited. We argue that this gap stems from misaligned incentives among L…
SAM2-SGP: Enhancing SAM2 for Medical Image Segmentation via Support-Set Guided Prompting
Yang Xing, Jiong Wu, Yuheng Bu +1
Although new vision foundation models such as Segment Anything Model 2 (SAM2) have significantly enhanced zero-shot image segmentation capabilities, reliance on human-provided prom…
Fairness Overfitting in Machine Learning: An Information-Theoretic Perspective
Firas Laakom, Haobo Chen, Jürgen Schmidhuber +1
Despite substantial progress in promoting fairness in high-stake applications using machine learning models, existing methods often modify the training process, such as through reg…
In-Context Watermarks for Large Language Models
Yepeng Liu, Xuandong Zhao, Christopher Kruegel +2
The growing use of large language models (LLMs) for sensitive applications has highlighted the need for effective watermarking techniques to ensure the provenance and accountabilit…
Defending LLM Watermarking Against Spoofing Attacks with Contrastive Representation Learning
Li An, Yujian Liu, Yepeng Liu +3
Watermarking has emerged as a promising technique for detecting texts generated by LLMs. Current research has primarily focused on three design criteria: high quality of the waterm…
Dataset Protection via Watermarked Canaries in Retrieval-Augmented LLMs
Yepeng Liu, Xuandong Zhao, Dawn Song +1
Retrieval-Augmented Generation (RAG) has become an effective method for enhancing large language models (LLMs) with up-to-date knowledge. However, it may pose a risk of copyright i…
Distributional Information Embedding: A Framework for Multi-bit Watermarking
Haiyun He, Yepeng Liu, Ziqiao Wang +2
This paper introduces a novel problem, distributional information embedding, motivated by the practical demands of multi-bit watermarking for large language models (LLMs). Unlike t…
Image Watermarks are Removable Using Controllable Regeneration from Clean Noise
Yepeng Liu, Yiren Song, Hai Ci +4
Image watermark techniques provide an effective way to assert ownership, deter misuse, and trace content sources, which has become increasingly essential in the era of large genera…
Theoretically Grounded Framework for LLM Watermarking: A Distribution-Adaptive Approach
Haiyun He, Yepeng Liu, Ziqiao Wang +2
Watermarking has emerged as a crucial method to distinguish AI-generated text from human-created text. Current watermarking approaches often lack formal optimality guarantees or ad…
Information-Theoretic Opacity-Enforcement in Markov Decision Processes
Chongyang Shi, Yuheng Bu, Jie Fu
The paper studies information-theoretic opacity, an information-flow privacy property, in a setting involving two agents: A planning agent who controls a stochastic system and an o…
Class-wise Generalization Error: an Information-Theoretic Analysis
Firas Laakom, Yuheng Bu, Moncef Gabbouj
Existing generalization theories of supervised learning typically take a holistic approach and provide bounds for the expected generalization over the whole data distribution, whic…
Adaptive Text Watermark for Large Language Models
Yepeng Liu, Yuheng Bu
The advancement of Large Language Models (LLMs) has led to increasing concerns about the misuse of AI-generated text, and watermarking for LLM-generated text has emerged as a poten…