9 citations · 16 across the 18 of their papers we have counts for
20 papers
The Scheduler Is a Hidden Retriever: How Asynchrony Shapes Evidence Acquisition in Search Agents
Ruiyang Ren, Yuhao Wang, Yinan Zhang +1
Language-model agents increasingly solve complex tasks through parallel reasoning and asynchronous information gathering. Controlled replay across two model families and three benc…
From Dissonance to Orchestration: Teacher Intervention in On-Policy Distillation
Yuhao Wang, Ruiyang Ren, Yinan Zhang +3
On-policy distillation (OPD) trains a student on its own reasoning trajectories using feedback from a stronger teacher. Teacher interventions can improve these trajectories, but al…
DocClaw: A Unified Agentic System for Intelligent Document Processing
Siqi Xiang, Zhipeng Xu, Yufei Liu +6
Intelligent document processing (IDP) encompasses a broad range of tasks, including optical character recognition (OCR), document question answering (DocQA), and key information ex…
Audio Interaction Model
Zhifei Xie, Zihang Liu, Ze An +8
Audio is continuous and interactive, yet most Large Audio Language Models (LALMs) remain offline and streaming systems usually specialize in ASR or spoken dialogue. We formalize th…
When In-Distribution Gains Fail: Evaluating Weak-to-Strong Reward Models under Preference Shift
Khoi Le, Tri Cao, Phong Nguyen +5
Weak-to-strong (W2S) generalization is a promising framework for scalable oversight, yet existing evaluations often test students under matched train-test distributions. Therefore,…
Mega-ASR: Towards In-the-wild^2 Speech Recognition via Scaling up Real-world Acoustic Simulation
Zhifei Xie, Kaiyu Pang, Haobin Zhang +4
Despite rapid advances in automatic speech recognition (ASR) and large audio-language models, robust recognition in real-world environments remains limited by an "acoustic robustne…
EVA-0: Test-Time Model Evolution with Only Two Forward Passes per Sample
Guohao Chen, Shuaicheng Niu, Geng Li +4
Test-time model evolution offers a promising way for deployed models to improve from unlabeled test-time experience, yet most existing methods depend on backpropagation (BP), which…
WeCon: An Efficient Weight-Conditioned Neural Solver for Multi-Objective Combinatorial Optimization Problems
Xuan Wu, Jinbiao Chen, Yang Li +7
Existing neural solvers for Multi-Objective Combinatorial Optimization Problems (MOCOPs) commonly adopt decomposition-based strategies that scalarize a MOCOP into multiple subprobl…
HiRO-Nav: Hybrid ReasOning Enables Efficient Embodied Navigation
He Zhao, Yijun Yang, Zichuan Lin +2
Embodied navigation agents built upon large reasoning models (LRMs) can handle complex, multimodal environmental input and perform grounded reasoning per step to improve sequential…
Graph Topology Information Enhanced Heterogeneous Graph Representation Learning
He Zhao, Zhiwei Zeng, Yongwei Wang +1
Real-world heterogeneous graphs are inherently noisy and usually not in the optimal graph structures for downstream tasks, which often adversely affects the performance of GRL mode…
Emulating Clinician Cognition via Self-Evolving Deep Clinical Research
Ruiyang Ren, Yuhao Wang, Yunsen Liang +8
Clinical diagnosis is a complex cognitive process, grounded in dynamic cue acquisition and continuous expertise accumulation. Yet most current artificial intelligence (AI) systems…
FreRA: A Frequency-Refined Augmentation for Contrastive Learning on Time Series Classification
Tian Tian, Chunyan Miao, Hangwei Qian
Contrastive learning has emerged as a competent approach for unsupervised representation learning. However, the design of an optimal augmentation strategy, although crucial for con…
SoftCoT++: Test-Time Scaling with Soft Chain-of-Thought Reasoning
Yige Xu, Xu Guo, Zhiwei Zeng +1
Test-Time Scaling (TTS) refers to approaches that improve reasoning performance by allocating extra computation during inference, without altering the model's parameters. While exi…
SoftCoT: Soft Chain-of-Thought for Efficient Reasoning with LLMs
Yige Xu, Xu Guo, Zhiwei Zeng +1
Chain-of-Thought (CoT) reasoning enables Large Language Models (LLMs) to solve complex reasoning tasks by generating intermediate reasoning steps. However, most existing approaches…
Generating Synthetic Datasets for Few-shot Prompt Tuning
Xu Guo, Zilin Du, Boyang Li +1
A major limitation of prompt tuning is its dependence on large labeled training datasets. Under few-shot learning settings, prompt tuning lags far behind full-model fine-tuning, li…
RevMUX: Data Multiplexing with Reversible Adapters for Efficient LLM Batch Inference
Yige Xu, Xu Guo, Zhiwei Zeng +1
Large language models (LLMs) have brought a great breakthrough to the natural language processing (NLP) community, while leading the challenge of handling concurrent customer queri…
PairCFR: Enhancing Model Training on Paired Counterfactually Augmented Data through Contrastive Learning
Xiaoqi Qiu, Yongjie Wang, Xu Guo +4
Counterfactually Augmented Data (CAD) involves creating new data samples by applying minimal yet sufficient modifications to flip the label of existing data samples to other classe…
HGAttack: Transferable Heterogeneous Graph Adversarial Attack
He Zhao, Zhiwei Zeng, Yongwei Wang +2
Heterogeneous Graph Neural Networks (HGNNs) are increasingly recognized for their performance in areas like the web and e-commerce, where resilience against adversarial attacks is…
CUDC: A Curiosity-Driven Unsupervised Data Collection Method with Adaptive Temporal Distances for Offline Reinforcement Learning
Chenyu Sun, Hangwei Qian, Chunyan Miao
Offline reinforcement learning (RL) aims to learn an effective policy from a pre-collected dataset. Most existing works are to develop sophisticated learning algorithms, with less…
Flexible and Robust Counterfactual Explanations with Minimal Satisfiable Perturbations
Yongjie Wang, Hangwei Qian, Yongjie Liu +2
Counterfactual explanations (CFEs) exemplify how to minimally modify a feature vector to achieve a different prediction for an instance. CFEs can enhance informational fairness and…