8 citations · 26 across the 32 of their papers we have counts for
13 papers · 1 filter
Preserving Reasoning Diversity in Reinforcement Learning with Verifiable Rewards via Adaptive Replay
Wen-Zhi Li, Sainyam Galhotra, Claire Cardie
Reinforcement Learning with Verifiable Rewards (RLVR) improves the reasoning capabilities of large language models, but often reduces the diversity of their reasoning behaviors. We…
Does On-Policy Distillation Need to Complete Every Rollout?
Zhengxin Zhang, Maosen Tang, Ning Wang +6
On-policy distillation (OPD) transfers teacher knowledge to a student through feedback on student-generated rollouts, but generating complete rollouts and computing per-token teach…
Target-Constrained Pooling for Trajectory Extrapolation
Ning Wang, Claire Cardie, Sainyam Galhotra
Trajectory extrapolation from a partial target trajectory is underdetermined, but completed related trajectories provide information about the unresolved continuation. We propose t…
AuthBench: A Large-Scale Multilingual Benchmark for Authorship Representation across Genres and Lengths
MaoXun Huang, Zhenxing Zhang, Claire Cardie
Authorship signals matter in settings where writing style carries identity: digital forensics, plagiarism analysis, account linking, misinformation investigation, and machine-gener…
MANTA: Multi-Agent Network Topology Adaptation for Self-Evolving Multi-Agent Systems
Mao-xun Huang, Jerry Wang, Yi-Cheng Lai +3
Large language model-based multi-agent systems improve complex problem solving through task decomposition, agent specialization, information exchange, and intermediate validation.…
HARP: Efficient Data Selection for Finetuning Large Language Models
Ning Wang, Zhengxin Zhang, Maosen Tang +3
Finetuning data selection requires balancing two competing goals: selecting examples that improve the downstream objective, and doing so without repeatedly finetuning models. Train…
Knowing but Not Showing: LLMs Recognize Ambiguity but Rarely Ask Clarifying Questions
Jinyan Su, Claire Cardie
User queries are often underspecified and may admit multiple valid interpretations. Rather than silently making assumptions about the user's intent, a helpful assistant should surf…
How Far Are We From True Auto-Research?
Zhengxin Zhang, Ning Wang, Sainyam Galhotra +1
Recent auto-research systems can produce complete papers, but feasibility is not the same as quality, and the field still lacks a systematic study of how good agent-generated paper…
CLIPer: Tailoring Diverse User Preference via Classifier-Guided Inference-Time Personalization
Jinyan Su, Jinpeng Zhou, Claire Cardie +1
Personalized LLMs can significantly enhance user experiences by tailoring responses to preferences such as helpfulness, conciseness, and humor. However, fine-tuning models to addre…
Bootstrapping Post-training Signals for Open-ended Tasks via Rubric-based Self-play on Pre-training Text
Chengyu Huang, Sheng-Yen Chou, Zhengxin Zhang +1
Self-play has recently emerged as a promising paradigm for post-training Large Language Models (LLMs). In self-play, the target LLM creates the task input (e.g., a question), which…
Token-weighted Direct Preference Optimization with Attention
Chengyu Huang, Zhuohang Li, Sheng-Yen Chou +1
Direct Preference Optimization (DPO) aligns Large Language Models with human preferences without the need for a separate reward model. However, DPO treats all tokens in responses e…
FIRE-Bench: Evaluating AI Agents on the Rediscovery of Scientific Insights
Zhen Wang, Fan Bai, Zhongyan Luo +9
Autonomous agents powered by large language models (LLMs) promise to accelerate scientific discovery end-to-end, but rigorously evaluating their capacity for verifiable discovery r…
MovieRecapsQA: A Multimodal Open-Ended Video Question-Answering Benchmark
Shaden Shaar, Bradon Thymes, Sirawut Chaixanien +2
Understanding real-world videos such as movies requires integrating visual and dialogue cues. Yet existing VideoQA benchmarks struggle to capture this multimodal reasoning and, giv…