Publications (31)
In Prospect and Retrospect: Reflective Memory Management for Long-term Personalized Dialogue Agents
Zhen Tan, Jun Yan, I-Hung Hsu +12
Large Language Models (LLMs) have made significant progress in open-ended dialogue, yet their inability to retain and retrieve relevant information from long-term interactions limi…
COMPASS: Enhancing Agent Long-Horizon Reasoning with Evolving Context
Guangya Wan, Mingyang Ling, Xiaoqi Ren +3
Long-horizon tasks that require sustained reasoning and multiple tool interactions remain challenging for LLM agents: small errors compound across steps, and even state-of-the-art…
ECONET: Effective Continual Pretraining of Language Models for Event Temporal Reasoning
Rujun Han, Xiang Ren, Nanyun Peng
While pre-trained language models (PTLMs) have achieved noticeable success on many NLP tasks, they still struggle for tasks that require event temporal reasoning, which is essentia…
Modeling Context in Answer Sentence Selection Systems on a Latency Budget
Rujun Han, Luca Soldaini, Alessandro Moschitti
Answer Sentence Selection (AS2) is an efficient approach for the design of open-domain Question Answering (QA) systems. In order to achieve low latency, traditional AS2 models scor…
Towards Compute-Optimal Many-Shot In-Context Learning
Shahriar Golchin, Yanfei Chen, Rujun Han +7
Long-context large language models (LLMs) are able to process inputs containing up to several million tokens. In the scope of in-context learning (ICL), this translates into using…
SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback
Fangyuan Xu, Rujun Han, Yanfei Chen +7
Deep search agents, which aim to answer complex questions requiring reasoning across multiple documents, can significantly speed up the information-seeking process. Collecting huma…
TORQUE: A Reading Comprehension Dataset of Temporal Ordering Questions
Qiang Ning, Hao Wu, Rujun Han +3
A critical part of reading is being able to understand the temporal relationships between events described in a passage of text, even when those relationships are not explicitly st…
RubricEM: Meta-RL with Rubric-guided Policy Decomposition beyond Verifiable Rewards
Gaotang Li, Bhavana Dalvi Mishra, Zifeng Wang +9
Training deep research agents, namely systems that plan, search, evaluate evidence, and synthesize long-form reports, pushes reinforcement learning beyond the regime of verifiable…
Semantic Compensation via Adversarial Removal for Robust Zero-Shot ECG Diagnosis
Hongjun Liu, Rujun Han, Leyu Zhou +1
Recent ECG--language pretraining methods enable zero-shot diagnosis by aligning cardiac signals with clinical text, but they do not explicitly model robustness to partial observati…
Deep Structured Neural Network for Event Temporal Relation Extraction
Rujun Han, I-Hung Hsu, Mu Yang +3
We propose a novel deep structured learning framework for event temporal relation extraction. The model consists of 1) a recurrent neural network (RNN) to learn scoring functions f…
CiteEval: Principle-Driven Citation Evaluation for Source Attribution
Yumo Xu, Peng Qi, Jifan Chen +7
Citation quality is crucial in information-seeking systems, directly influencing trust and the effectiveness of information access. Current evaluation frameworks, both human and au…
Reverse Thinking Makes LLMs Stronger Reasoners
Justin Chih-Yao Chen, Zifeng Wang, Hamid Palangi +8
Reverse thinking plays a crucial role in human reasoning. Humans can reason not only from a problem to a solution but also in reverse, i.e., start from the solution and reason towa…
ACCENT: An Automatic Event Commonsense Evaluation Metric for Open-Domain Dialogue Systems
Sarik Ghazarian, Yijia Shao, Rujun Han +2
Commonsense reasoning is omnipresent in human communications and thus is an important feature for open-domain dialogue systems. However, evaluating commonsense in dialogue systems…
RAG-QA Arena: Evaluating Domain Robustness for Long-form Retrieval Augmented Question Answering
Rujun Han, Yuhao Zhang, Peng Qi +6
Question answering based on retrieval augmented generation (RAG-QA) is an important research topic in NLP and has a wide range of real-world applications. However, most existing da…
Deep Researcher with Test-Time Diffusion
Rujun Han, Yanfei Chen, Zoey CuiZhu +15
Deep research agents, powered by Large Language Models (LLMs), are rapidly advancing; yet, their performance often plateaus when generating complex, long-form research reports usin…
Joint Event and Temporal Relation Extraction with Shared Representations and Structured Prediction
Rujun Han, Qiang Ning, Nanyun Peng
We propose a joint event and temporal relation extraction model with shared representation learning and structured prediction. The proposed method has two advantages over existing…
Clinical Temporal Relation Extraction with Probabilistic Soft Logic Regularization and Global Inference
Yichao Zhou, Yu Yan, Rujun Han +5
There has been a steady need in the medical community to precisely extract the temporal relations between clinical events. In particular, temporal information can facilitate a vari…
FinanceHarness: Autonomous Financial Deep Research Framework
Yijia Xiao, Rujun Han, Yanfei Chen +8
The paper introduces FinanceHarness, a framework that uses large language models and autonomous agents to automate end‑to‑end financial deep research, and presents FinanceGym, a be…
Supervised Reinforcement Learning: From Expert Trajectories to Step-wise Reasoning
Yihe Deng, I-Hung Hsu, Jun Yan +7
Large Language Models (LLMs) often struggle with problems that require multi-step reasoning. For small-scale open-source models, Reinforcement Learning with Verifiable Rewards (RLV…
Budget-Aware Tool-Use Enables Effective Agent Scaling
Tengxiao Liu, Zifeng Wang, Jin Miao +12
Scaling test-time computation improves performance across different tasks on large language models (LLMs), which has also been extended to tool-augmented agents. For these agents,…
EventPlus: A Temporal Event Understanding Pipeline
Mingyu Derek Ma, Jiao Sun, Mu Yang +5
We present EventPlus, a temporal event understanding pipeline that integrates various state-of-the-art event understanding components including event trigger and type detection, ev…
ReasoningBank: Scaling Agent Self-Evolving with Reasoning Memory
Siru Ouyang, Jun Yan, I-Hung Hsu +14
With the growing adoption of large language model agents in persistent real-world roles, they naturally encounter continuous streams of tasks. A key limitation, however, is their f…
Dancing in Chains: Reconciling Instruction Following and Faithfulness in Language Models
Zhengxuan Wu, Yuhao Zhang, Peng Qi +6
Modern language models (LMs) need to follow human instructions while being faithful; yet, they often fail to achieve both. Here, we provide concrete evidence of a trade-off between…
Domain Knowledge Empowered Structured Neural Net for End-to-End Event Temporal Relation Extraction
Rujun Han, Yichao Zhou, Nanyun Peng
Extracting event temporal relations is a critical task for information extraction and plays an important role in natural language understanding. Prior systems leverage deep learnin…
SkillOS: Learning Skill Curation for Self-Evolving Agents
Siru Ouyang, Jun Yan, Yanfei Chen +13
LLM-based agents are increasingly deployed to handle streaming tasks, yet they often remain one-off problem solvers that fail to learn from past interactions. Reusable skills disti…
Speculative Knowledge Distillation: Bridging the Teacher-Student Gap Through Interleaved Sampling
Wenda Xu, Rujun Han, Zifeng Wang +7
Recent advances in knowledge distillation (KD) have enabled smaller student models to approach the performance of larger teacher models. However, popular methods such as supervised…
Contextualized Word Embeddings Enhanced Event Temporal Relation Extraction for Story Understanding
Rujun Han, Mengyue Liang, Bashar Alhafni +1
Learning causal and temporal relationships between events is an important step towards deeper story and commonsense understanding. Though there are abundant datasets annotated with…
CAFE: Channel-Autoregressive Factorized Encoding for Robust Biosignal Spatial Super-Resolution
Hongjun Liu, Leyu Zhou, Zijianghao Yang +4
High-density biosignal recordings are critical for neural decoding and clinical monitoring, yet real-world deployments often rely on low-density (LD) montages due to hardware and o…
Character-Centric Story Visualization via Visual Planning and Token Alignment
Hong Chen, Rujun Han, Te-Lin Wu +2
Story visualization advances the traditional text-to-image generation by enabling multiple image generation based on a complete story. This task requires machines to 1) understand…
ESTER: A Machine Reading Comprehension Dataset for Event Semantic Relation Reasoning
Rujun Han, I-Hung Hsu, Jiao Sun +4
Understanding how events are semantically related to each other is the essence of reading comprehension. Recent event-centric reading comprehension datasets focus mostly on event a…
Go Back in Time: Generating Flashbacks in Stories with Event Temporal Prompts
Rujun Han, Hong Chen, Yufei Tian +1
Stories or narratives are comprised of a sequence of events. To compose interesting stories, professional writers often leverage a creative writing technique called flashback that…