5 citations · 6 across the 13 of their papers we have counts for
14 papers
CURIO: Curiosity-Driven Test-Time Learning for Open-Ended Discovery
Tao Feng, Fangxu Yu, Zijie Lei +5
Open-ended discovery requires learning from repeated attempts while continuing to explore directions whose value is not yet apparent. Search with a frozen large language model (LLM…
LLMRouter: Unified Infrastructure for Developing, Evaluating, and Deploying LLM Routers
Tao Feng, Fangxu Yu, Haozhen Zhang +9
No single large language model (LLM) is optimal across all queries and budget constraints, making model routing essential for cost-effective deployment. Existing routers adopt dive…
Reinforcement Learning with Evolving Rubrics as Rewards for Audio Reasoning
Fangxu Yu, Tao Feng, Dehai Min +6
Audio reasoning is essential for machine understanding of the acoustic world. Reinforcement learning with verifiable rewards can elicit such reasoning, yet existing reward designs…
Weak-to-Strong On-Policy Distillation
Fangxu Yu, Weijia Xu, Michael Xu +2
On-policy distillation (OPD), which aligns a student with the teacher's token-level distribution on the student's own rollouts, is an effective paradigm for transferring capabiliti…
TSRouter: Dynamic Modality-Model Selection for Time Series Reasoning
Fangxu Yu, Tao Feng, Dehai Min +3
Time series reasoning is essential for real-world problem-solving. While both Large Language Models (LLMs) and Vision-Language Models (VLMs) can reason about time-series data, thei…
FlowBank: Query-Adaptive Agentic Workflows Optimization through Precompute-and-Reuse
Lingzhi Yuan, Chenghao Deng, Fangxu Yu +3
Large Language Model (LLM)-based multi-agent systems are increasingly powerful, but current agentic workflow optimization paradigms make an unsatisfying trade-off. Task-level metho…
TSRBench: A Comprehensive Multi-task Multi-modal Time Series Reasoning Benchmark for Generalist Models
Fangxu Yu, Xingang Guo, Lingzhi Yuan +6
Time series are ubiquitous in real-world scenarios and crucial for applications ranging from energy management to traffic control. Consequently, the ability to reason over time ser…
ArrowGEV: Grounding Events in Video via Learning the Arrow of Time
Fangxu Yu, Ziyao Lu, Liqiang Niu +2
Grounding events in videos serves as a fundamental capability in video analysis. While Vision Language Models (VLMs) are increasingly employed for this task, existing approaches pr…
ArcMemo: Abstract Reasoning Composition with Lifelong LLM Memory
Matthew Ho, Chen Si, Zhaoxiang Feng +5
While inference-time scaling enables LLMs to carry out increasingly long and capable reasoning traces, the patterns and insights uncovered during these traces are immediately disca…
TS-Reasoner: Aligning Time Series Foundation Models with LLM Reasoning
Fangxu Yu, Hongyu Zhao, Tianyi Zhou
Time series reasoning is crucial to decision-making in diverse domains, including finance, energy, and scientific discovery. While existing time series foundation models (TSFMs) ca…
PersuasiveToM: A Benchmark for Evaluating Machine Theory of Mind in Persuasive Dialogues
Fangxu Yu, Lai Jiang, Shenyi Huang +2
The ability to understand and predict the mental states of oneself and others, known as the Theory of Mind (ToM), is crucial for effective social scenarios. Although recent studies…
Flow of Reasoning: Training LLMs for Divergent Reasoning with Minimal Examples
Fangxu Yu, Lai Jiang, Haoqiang Kang +2
The ability to generate diverse solutions to a given problem is a hallmark of human creativity. This divergent reasoning is also crucial for machines, enhancing their robustness an…
Emotion-Anchored Contrastive Learning Framework for Emotion Recognition in Conversation
Fangxu Yu, Junjie Guo, Zhen Wu +1
Emotion Recognition in Conversation (ERC) involves detecting the underlying emotion behind each utterance within a conversation. Effectively generating representations for utteranc…
COLD-Attack: Jailbreaking LLMs with Stealthiness and Controllability
Xingang Guo, Fangxu Yu, Huan Zhang +2
Jailbreaks on large language models (LLMs) have recently received increasing attention. For a comprehensive assessment of LLM safety, it is essential to consider jailbreaks with di…