1 citations · 1 across the 16 of their papers we have counts for
20 papers
Exact Risk Certificates for Pairwise-Judged Reranking
Xinyu Wang, Jingrui Tian, Sicheng Lyu +4
Pairwise relevance judgments constrain both the loss numerator and the ideal-ranking denominator of nDCG. We characterize the exact worst-case loss of replacing a ranking with a fi…
Measuring the Task Value of Precision Upgrades in Closed-Loop Agents
Sicheng Lyu, Xinyu Wang, Yu Gu +3
A low-precision agent can call its full-precision (BF16) model at selected decisions as a fallback. A learned precision router chooses where to call it from the disagreement betwee…
From Mathematical to Executable Certificates for Machine Unlearning
Ziyu Zhao, Xinyu Wang, Xiaowen Chang +1
Machine unlearning is needed when data must be removed because of deletion requests, outdated records, or data-quality concerns, while retraining from scratch can be costly. Certif…
Sequential Functional Structured Tucker Compression for Large Language Model Attentions
Jiangfeng Chen, Xinyu Wang, Tianshuo Yan +4
Post-training compression of LLM attention is often formulated as independent matrix approximation, ignoring both the shared structure among attention projections and the represent…
Alignment Drift in Single-Model Speculative Decoding for ASR: Mechanism, Correction, and Cost
Xinyu Wang, Huapeng Zhou, Ziyu Zhao +5
Speculative decoding speeds up generation by letting a cheap draft propose several tokens that a target model checks in one pass. In the single-model form, the draft is a lightweig…
RRC: Unlocking Generative Reward Models in LLM Reinforcement Learning via Ranking-Based Reward Construction
Chenglong Wang, Ziming Zhu, Yifu Huo +9
Recent advances in reward modeling show a paradigm shift from discriminative reward models to generative reward models. However, despite their strong capabilities in response ranki…
CoRe: A Continuously Reward-Finetuned LLM Query Rewriter for Multi-Stage Context-Aware Relevance in Web-Scale Video Search
Yilin Wen, Rong Yang, Xiaojia Chang +11
LLM-based query rewriters in production face a tension: the training reward must reflect how the rewrite is consumed by the production ranker, yet the training procedure must be ch…
TARQ: Tail-Aware Reconstruction Quantization for Rare-Word Robust Automatic Speech Recognition
Xinyu Wang, Ziyu Zhao, Ke Bai +4
Data-aware post-training quantization (PTQ) minimizes a per-token reconstruction loss on a small calibration corpus, implicitly weighting positions by their empirical frequency. Fo…
SPS: Steering Probability Squeezing for Better Exploration in Reinforcement Learning for Large Language Models
Yifu Huo, Chenglong Wang, Ziming Zhu +9
Reinforcement learning (RL) has emerged as a promising paradigm for training reasoning-oriented models by leveraging rule-based reward signals. However, RL training typically tends…
OJBKQ: Objective-Joint Babai-Klein Quantization
Xinyu Wang, Ziyu Zhao, Peng Lu +2
Post-training quantization (PTQ) is widely used to compress large language models without retraining. However, many existing weight-only methods rely on heuristic objectives and gr…
InfMem: Learning System-2 Memory Control for Long-Context Agent
Xinyu Wang, Mingze Li, Peng Lu +6
Reasoning over ultra-long documents requires synthesizing sparse evidence scattered across distant segments under strict memory constraints. While streaming agents enable scalable…
Farewell to Item IDs: Unlocking the Scaling Potential of Large Ranking Models via Semantic Tokens
Zhen Zhao, Tong Zhang, Jie Xu +5
Recent studies on scaling up ranking models have achieved substantial improvement for recommendation systems and search engines. However, most large-scale ranking systems rely on i…
Beyond Hard Writes and Rigid Preservation: Soft Recursive Least-Squares for Lifelong LLM Editing
Xinyu Wang, Sicheng Lyu, Yu Gu +4
Model editing updates a pre-trained LLM with new facts or rules without retraining while preserving unrelated behavior. In real deployment, edits arrive as long streams, creating a…
MARS: Unleashing the Power of Speculative Decoding via Margin-Aware Verification
Jingwei Song, Xinyu Wang, Hanbin Wang +6
Speculative Decoding (SD) accelerates autoregressive large language model (LLM) inference by decoupling generation and verification. While recent methods improve draft quality by t…
SERM: Self-Evolving Relevance Model with Agent-Driven Learning from Massive Query Streams
Chenglong Wang, Canjia Li, Xingzhao Zhu +9
Due to the dynamically evolving nature of real-world query streams, relevance models struggle to generalize to practical search scenarios. A sophisticated solution is self-evolutio…
Diagnostic-Driven Layer-Wise Compensation for Post-Training Quantization of Encoder-Decoder ASR Models
Xinyu Wang, Ziyu Zhao, Yajie Luo +6
Layer-wise post-training quantization reconstructs each layer from inputs already altered by the quantized prefix. QEP compensates for this drift with one model-wide coefficient, c…
EvoEdit: Evolving Null-space Alignment for Robust and Efficient Knowledge Editing
Sicheng Lyu, Yu Gu, Xinyu Wang +5
Large language models (LLMs) require continual updates to rectify outdated or erroneous knowledge. Model editing has emerged as a compelling paradigm for introducing targeted modif…
Improving Context Fidelity via Native Retrieval-Augmented Reasoning
Suyuchen Wang, Jinlin Wang, Xinyu Wang +6
Large language models (LLMs) often struggle with context fidelity, producing inconsistent answers when responding to questions based on provided information. Existing approaches ei…
PoTPTQ: A Two-step Power-of-Two Post-training for LLMs
Xinyu Wang, Vahid Partovi Nia, Peng Lu +4
Large Language Models (LLMs) have demonstrated remarkable performance across various natural language processing (NLP) tasks. However, their deployment is challenging due to the su…
Resona: Improving Context Copying in Linear Recurrence Models with Retrieval
Xinyu Wang, Linrui Ma, Jerry Huang +5
Recent shifts in the space of large language model (LLM) research have shown an increasing focus on novel architectures to compete with prototypical Transformer-based models that h…