8 citations · 15 across the 14 of their papers we have counts for
19 papers
Who May Release an Agent's Promise? Standing over Commitments in Multi-Party Chat
Lan Wei, Bingyu Shen, Jiaqi Tang +6
When an assistant serving a team makes a promise to Alice, who may cancel it? We call this standing: only the creditor (the person owed) or someone the creditor or operator policy…
Executable Prefix Values for Locating Agent Failures
Bingyu Shen, Jiaqi Tang, Lan Wei +3
Work on debugging LLM agents treats the "first mistake" marked by a human or LLM judge as ground truth for where a trajectory failed. We ask whether such labels point at causes or…
Decision-Sufficient State Representations: Measuring and Reducing Write-Time Regret
Bingyu Shen, Boyang Li
Long tasks produce more history than an LLM agent can hold in its context, and more than it uses reliably even when the history fits. A growing line of work therefore has agents ca…
Sequential Beats Joint: On the Interplay between On-Policy Distillation and RLVR
Boyan Li, Bingsen Chen, Chenghao Yang +3
Reinforcement learning with verifiable rewards (RLVR) and on-policy distillation (OPD) have emerged as two dominant methods for post-training reasoning LLMs. Prior work uses OPD's…
LLM-as-Judge Framework for Evaluating Tone-Induced Hallucination in Vision-Language Models
Zhiyuan Jiang, Weihao Hong, Xinlei Guan +8
Vision-Language Models (VLMs) are increasingly deployed in settings where reliable visual grounding carries operational consequences, yet their behavior under progressively coerciv…
HadAgent: Harness-Aware Decentralized Agentic AI Serving with Proof-of-Inference Blockchain Consensus
Landy Jimenez, Mariah Weatherspoon, Bingyu Shen +3
Proof-of-Work (PoW) blockchain consensus consumes vast computational resources without producing useful output, while the rapid growth of large language model (LLM) agents has crea…
InstrAct: Towards Action-Centric Understanding in Instructional Videos
Zhuoyi Yang, Jiapeng Yu, Reuben Tan +2
Understanding instructional videos requires recognizing fine-grained actions and modeling their temporal relations, which remains challenging for current Video Foundation Models (V…
Beyond Single-shot Writing: Deep Research Agents are Unreliable at Multi-turn Report Revision
Bingsen Chen, Boyan Li, Ping Nie +3
Existing benchmarks for Deep Research Agents (DRAs) treat report generation as a single-shot writing task, which fundamentally diverges from how human researchers iteratively draft…
Injecting Knowledge from Social Science Journals to Improve Indonesian Cultural Understanding by LLMs
Adimulya Kartiyasa, Bao Gia Cao, Boyang Li
Recently there have been intensifying efforts to improve the understanding of Indonesian cultures by large language models (LLMs). An attractive source of cultural knowledge that h…
Tone Matters: The Impact of Linguistic Tone on Hallucination in VLMs
Weihao Hong, Zhiyuan Jiang, Bingyu Shen +4
Vision-Language Models (VLMs) are increasingly used in safety-critical applications that require reliable visual grounding. However, these models often hallucinate details that are…
Learning to Refuse: Refusal-Aware Reinforcement Fine-Tuning for Hard-Irrelevant Queries in Video Temporal Grounding
Jin-Seop Lee, SungJoon Lee, SeongJun Jung +2
Video Temporal Grounding (VTG) aims to localize a temporal segment in a video corresponding to a natural language query. However, existing VTG models assume that a relevant segment…
Test-time Scaling of LLMs: A Survey from A Subproblem Structure Perspective
Zhuoyi Yang, Xu Guo, Tong Zhang +2
With this paper, we survey techniques for improving the predictive accuracy of pretrained large language models by allocating additional compute at inference time. In categorizing…
Two Causally Related Needles in a Video Haystack
Miaoyu Li, Qin Chao, Boyang Li
Properly evaluating the ability of Video-Language Models (VLMs) to understand long videos remains a challenge. We propose a long-context video understanding benchmark, Causal2Needl…
Generating Synthetic Datasets for Few-shot Prompt Tuning
Xu Guo, Zilin Du, Boyang Li +1
A major limitation of prompt tuning is its dependence on large labeled training datasets. Under few-shot learning settings, prompt tuning lags far behind full-model fine-tuning, li…
ErrorRadar: Benchmarking Complex Mathematical Reasoning of Multimodal Large Language Models Via Error Detection
Yibo Yan, Shen Wang, Jiahao Huo +13
As the field of Multimodal Large Language Models (MLLMs) continues to evolve, their potential to revolutionize artificial intelligence is particularly promising, especially in addr…
A Training Data Recipe to Accelerate A* Search with Language Models
Devaansh Gupta, Boyang Li
Combining Large Language Models (LLMs) with heuristic search algorithms like A* holds the promise of enhanced LLM reasoning and scalable inference. To accelerate training and reduc…
Training on Synthetic Data Beats Real Data in Multimodal Relation Extraction
Zilin Du, Haoxin Li, Xu Guo +1
The task of multimodal relation extraction has attracted significant research attention, but progress is constrained by the scarcity of available training data. One natural thought…
Uncovering Prototypical Knowledge for Weakly Open-Vocabulary Semantic Segmentation
Fei Zhang, Tianfei Zhou, Boyang Li +6
This paper studies the problem of weakly open-vocabulary semantic segmentation (WOVSS), which learns to segment objects of arbitrary classes using mere image-text pairs. Existing w…
Annotating High-Level Structures of Short Stories and Personal Anecdotes
Boyang Li, Beth Cardier, Tong Wang +1
Stories are a vital form of communication in human culture; they are employed daily to persuade, to elicit sympathy, or to convey a message. Computational understanding of human na…