5 citations · 25 across the 26 of their papers we have counts for
26 papers
BiCAA: Bidirectional Credit Assignment for Search-Augmented Agent
Yibin Huang, Bin Xu, Hailong Cao +1
Multi-step search is a fundamental capability for search agents, enabling them to iteratively acquire, refine, and integrate external evidence for complex reasoning QA. However, va…
SPAE: Spectrally Guided Autoencoder for Pretrained Visual Latents
Yibin Huang, Jixiang Hong, Zongzhao Li +8
Latents from vision foundation models (VFMs) are semantically rich and well suited for visual understanding. Recent representation autoencoder methods such as RAE have shown that t…
Long-form RewardBench: Evaluating Reward Models for Long-form Generation
Hui Huang, Yancheng He, Wei Liu +7
The widespread adoption of reinforcement learning-based alignment highlights the growing importance of reward models. Various benchmarks have been built to evaluate reward models i…
Toward Robust LLM-Based Judges: Taxonomic Bias Evaluation and Debiasing Optimization
Hongli Zhou, Hui Huang, Rui Zhang +5
Large language model (LLM)-based judges are widely adopted for automated evaluation and reward modeling, yet their judgments are often affected by judgment biases. Accurately evalu…
From Perception to Reasoning: Deep Thinking Empowers Multimodal Large Language Models
Wenxin Zhu, Andong Chen, Yuchen Song +4
With the remarkable success of Multimodal Large Language Models (MLLMs) in perception tasks, enhancing their complex reasoning capabilities has emerged as a critical research focus…
Video2Layout: Recall and Reconstruct Metric-Grounded Cognitive Map for Spatial Reasoning
Yibin Huang, Wang Xu, Wanyue Zhang +6
Spatial intelligence is a critical frontier for Multimodal Large Language Models (MLLMs), empowering them to comprehend the physical world. Drawing inspiration from human perceptio…
Speculative Decoding Meets Quantization: Compatibility Evaluation and Hierarchical Framework Design
Yudi Zhang, Weilin Zhao, Xu Han +4
Speculative decoding and quantization effectively accelerate memory-bound inference of large language models. Speculative decoding mitigates the memory bandwidth bottleneck by veri…
Lost in Benchmarks? Rethinking Large Language Model Benchmarking with Item Response Theory
Hongli Zhou, Hui Huang, Ziqing Zhao +10
The evaluation of large language models (LLMs) via benchmarks is widespread, yet inconsistencies between different leaderboards and poor separability among top models raise concern…
DuplexMamba: Enhancing Real-time Speech Conversations with Duplex and Streaming Capabilities
Xiangyu Lu, Wang Xu, Haoyu Wang +5
Real-time speech conversation is essential for natural and efficient human-machine interactions, requiring duplex and streaming capabilities. Traditional Transformer-based conversa…
MuSC: Improving Complex Instruction Following with Multi-granularity Self-Contrastive Training
Hui Huang, Jiaheng Liu, Yancheng He +5
Complex instruction-following with elaborate constraints is imperative for Large Language Models (LLMs). While existing methods have constructed data for complex instruction alignm…
SEO: Stochastic Experience Optimization for Large Language Models
Jitao Xu, Hongyun Zhou, Lei Shen +3
Large Language Models (LLMs) can benefit from useful experiences to improve their performance on specific tasks. However, finding helpful experiences for different LLMs is not obvi…
Mitigating the Bias of Large Language Model Evaluation
Hongli Zhou, Hui Huang, Yunfei Long +5
Recently, there has been a trend of evaluating the Large Language Model (LLM) quality in the flavor of LLM-as-a-Judge, namely leveraging another LLM to evaluate the current output…
LoRA-drop: Efficient LoRA Parameter Pruning based on Output Evaluation
Hongyun Zhou, Xiangyu Lu, Wang Xu +3
Low-Rank Adaptation (LoRA) is currently the most commonly used Parameter-efficient fine-tuning (PEFT) method, it introduces auxiliary parameters for each layer to fine-tune the pre…
CLMLF:A Contrastive Learning and Multi-Layer Fusion Method for Multimodal Sentiment Detection
Zhen Li, Bing Xu, Conghui Zhu +1
Compared with unimodal data, multimodal data can provide more features to help the model analyze the sentiment of data. Previous research works rarely consider token-level feature…
A Neural Conversation Generation Model via Equivalent Shared Memory Investigation
Changzhen Ji, Yating Zhang, Xiaozhong Liu +4
Conversation generation as a challenging task in Natural Language Generation (NLG) has been increasingly attracting attention over the last years. A number of recent works adopted…
AI-lead Court Debate Case Investigation
Changzhen Ji, Xin Zhou, Conghui Zhu +1
The multi-role judicial debate composed of the plaintiff, defendant, and judge is an important part of the judicial trial. Different from other types of dialogue, questions are rai…
Cross Copy Network for Dialogue Generation
Changzhen Ji, Xin Zhou, Yating Zhang +4
In the past few years, audiences from different fields witness the achievements of sequence-to-sequence models (e.g., LSTM+attention, Pointer Generator Networks, and Transformer) t…
Reliable Evaluations for Natural Language Inference based on a Unified Cross-dataset Benchmark
Guanhua Zhang, Bing Bai, Jian Liang +3
Recent studies show that crowd-sourced Natural Language Inference (NLI) datasets may suffer from significant biases like annotation artifacts. Models utilizing these superficial cl…
Understanding Learning Dynamics for Neural Machine Translation
Conghui Zhu, Guanlin Li, Lemao Liu +2
Despite the great success of NMT, there still remains a severe challenge: it is hard to interpret the internal dynamics during its training process. In this paper we propose to und…
Detecting and Understanding Generalization Barriers for Neural Machine Translation
Guanlin Li, Lemao Liu, Conghui Zhu +2
Generalization to unseen instances is our eternal pursuit for all data-driven models. However, for realistic task like machine translation, the traditional approach measuring gener…
Demographics Should Not Be the Reason of Toxicity: Mitigating Discrimination in Text Classifications with Instance Weighting
Guanhua Zhang, Bing Bai, Junqi Zhang +3
With the recent proliferation of the use of text classifications, researchers have found that there are certain unintended biases in text classification datasets. For example, text…
Modeling Future Cost for Neural Machine Translation
Chaoqun Duan, Kehai Chen, Rui Wang +4
Existing neural machine translation (NMT) systems utilize sequence-to-sequence neural networks to generate target translation word by word, and then make the generated word at each…
Multimodal Matching Transformer for Live Commenting
Chaoqun Duan, Lei Cui, Shuming Ma +3
Automatic live commenting aims to provide real-time comments on videos for viewers. It encourages users engagement on online video sites, and is also a good benchmark for video-to-…
Mitigating Annotation Artifacts in Natural Language Inference Datasets to Improve Cross-dataset Generalization Ability
Guanhua Zhang, Bing Bai, Junqi Zhang +3
Natural language inference (NLI) aims at predicting the relationship between a given pair of premise and hypothesis. However, several works have found that there widely exists a bi…