7 citations · 9 across the 21 of their papers we have counts for
10 papers · 1 filter
Adapting Context Compression for Long-Horizon Agents with Counterfactual Continuations
Guanghui Min, Liang Wu, Mingjia Shi +4
Long-horizon agents require context compression to manage growing interaction histories. Compression quality, however, is ultimately determined by downstream execution. Existing pr…
S^3martCirc: Self-supervised Smart Circuit Discovery
Wendy Zheng, Yinhan He, Liang Wu +1
Large Language Models (LLMs) have demonstrated remarkable performance across diverse tasks, from text summarization to question answering. Despite these capabilities, their black-b…
Every Token Leaves a Ripple in the Stream of Thought: Eliciting Model-Internal Token Saliency for Chain-of-Thought Compression
Tianyi Zhao, Yinhan He, Wendy Zheng +2
Chain-of-thought (CoT) reasoning improves multi-step problem solving, but long reasoning traces inflate inference cost. Token-level CoT compression reduces this cost by pruning ful…
Implicit Reasoning for Large Language Model-based Generative Recommendation
Yinhan He, Liam Collins, Bhuvesh Kumar +3
Large Language Models (LLMs) are increasingly adopted as backbones for Generative Recommendation (GR), promising access to pretrained world knowledge. Yet reliably invoking this kn…
Mult-DPO: Multinomial Direct Preference Optimization for Recommender Systems
Yaochen Zhu, Harald Steck, James McInerney +4
Direct preference optimization (DPO) is a simple and effective alignment strategy for large language models (LLMs) based on pairwise preferences. In recommender systems, however, u…
Wired for Overconfidence: A Mechanistic Perspective on Inflated Verbalized Confidence in LLMs
Tianyi Zhao, Yinhan He, Wendy Zheng +2
Large language models are often not just wrong, but \emph{confidently wrong}: when they produce factually incorrect answers, they tend to verbalize overly high confidence rather th…
Reforming the Mechanism: Editing Reasoning Patterns in LLMs with Circuit Reshaping
Zhenyu Lei, Qiong Wu, Jianxiong Dong +4
Large language models (LLMs) often exhibit flawed reasoning ability that undermines reliability. Existing approaches to improving reasoning typically treat it as a general and mono…
Saliency-Aware Multi-Route Thinking: Revisiting Vision-Language Reasoning
Mingjia Shi, Yinhan He, Yaochen Zhu +1
Vision-language models (VLMs) aim to reason by jointly leveraging visual and textual modalities. While allocating additional inference-time computation has proven effective for lar…
PhysicsAgentABM: Physics-Guided Generative Agent-Based Modeling
Kavana Venkatesh, Yinhan He, Jundong Li +1
Large language model (LLM)-based multi-agent systems enable expressive agent reasoning but are expensive to scale and poorly calibrated for timestep-aligned state-transition simula…
IAPO: Information-Aware Policy Optimization for Token-Efficient Reasoning
Yinhan He, Yaochen Zhu, Mingjia Shi +5
Large language models increasingly rely on long chains of thought to improve accuracy, yet such gains come with substantial inference-time costs. We revisit token-efficient post-tr…