17 citations · 50 across the 27 of their papers we have counts for
26 papers · 1 filter
PersonaForge: Realistic Multi-Turn User Simulation for Agentic Systems
Hanglong Lv, Dawei Zhu, Lei Li +11
Large language models are increasingly used as agentic workflow executors, yet existing training data and benchmarks largely assume informationally complete, single-turn queries. O…
DFlare: Scaling Up Draft Capacity for Block Diffusion Speculative Decoding
Jiebin Zhang, Zhenghan Yu, Song Liu +9
Block diffusion speculative decoding accelerates LLM inference by predicting all tokens within a block simultaneously for the target model to verify in parallel. Predicting an enti…
Hy-MT2: A Family of Fast, Efficient and Powerful Multilingual Translation Models in the Wild
Mao Zheng, Zheng Li, Tao Chen +10
Hy-MT2 is a family of fast-thinking multilingual translation models designed for complex real-world scenarios. It includes three model sizes: 1.8B, 7B, and 30B-A3B (MoE), all of wh…
Learning to Draft: Adaptive Speculative Decoding with Reinforcement Learning
Jiebin Zhang, Zhenghan Yu, Liang Wang +8
Speculative decoding accelerates large language model (LLM) inference by using a small draft model to generate candidate tokens for a larger target model to verify. The efficacy of…
Hierarchical Memory Organization for Wikipedia Generation
Eugene J. Yu, Dawei Zhu, Yifan Song +6
Generating Wikipedia articles autonomously is a challenging task requiring the integration of accurate, comprehensive, and well-structured information from diverse sources. This pa…
More Vulnerable than You Think: On the Stability of Tool-Integrated LLM Agents
Weimin Xiong, Ke Wang, Yifan Song +4
Current evaluations of tool-integrated LLM agents typically focus on end-to-end tool-usage evaluation while neglecting their stability. This limits their real-world applicability,…
A Comprehensive Survey on Long Context Language Modeling
Jiaheng Liu, Dawei Zhu, Zhiqi Bai +34
Efficient processing of long contexts has been a persistent pursuit in Natural Language Processing. With the growing number of long documents, dialogues, and other textual data, it…
MPO: Boosting LLM Agents with Meta Plan Optimization
Weimin Xiong, Yifan Song, Qingxiu Dong +4
Recent advancements in large language models (LLMs) have enabled LLM-based agents to successfully tackle interactive planning tasks. However, despite their successes, existing appr…
More Tokens, Lower Precision: Towards the Optimal Token-Precision Trade-off in KV Cache Compression
Jiebin Zhang, Dawei Zhu, Yifan Song +6
As large language models (LLMs) process increasing context windows, the memory usage of KV cache has become a critical bottleneck during inference. The mainstream KV compression me…
AgentBank: Towards Generalized LLM Agents via Fine-Tuning on 50000+ Interaction Trajectories
Yifan Song, Weimin Xiong, Xiutian Zhao +6
Fine-tuning on agent-environment interaction trajectory data holds significant promise for surfacing generalized agent capabilities in open-source large language models (LLMs). In…
The Good, The Bad, and The Greedy: Evaluation of LLMs Should Not Ignore Non-Determinism
Yifan Song, Guoyin Wang, Sujian Li +1
Current evaluations of large language models (LLMs) often overlook non-determinism, typically focusing on a single output per example. This limits our understanding of LLM performa…
Watch Every Step! LLM Agent Learning via Iterative Step-Level Process Refinement
Weimin Xiong, Yifan Song, Xiutian Zhao +6
Large language model agents have exhibited exceptional performance across a range of complex interactive tasks. Recent approaches have utilized tuning with expert trajectories to e…
VisualWebBench: How Far Have Multimodal LLMs Evolved in Web Page Understanding and Grounding?
Junpeng Liu, Yifan Song, Bill Yuchen Lin +4
Multimodal Large Language models (MLLMs) have shown promise in web-related tasks, but evaluating their performance in the web domain remains a challenge due to the lack of comprehe…
LongEmbed: Extending Embedding Models for Long Context Retrieval
Dawei Zhu, Liang Wang, Nan Yang +4
Embedding models play a pivot role in modern NLP applications such as IR and RAG. While the context limit of LLMs has been pushed beyond 1 million tokens, embedding models are stil…
CoUDA: Coherence Evaluation via Unified Data Augmentation
Dawei Zhu, Wenhao Wu, Yifan Song +3
Coherence evaluation aims to assess the organization and structure of a discourse, which remains challenging even in the era of large language models. Due to the scarcity of annota…
Trial and Error: Exploration-Based Trajectory Optimization for LLM Agents
Yifan Song, Da Yin, Xiang Yue +3
Large Language Models (LLMs) have become integral components in various autonomous agent systems. In this study, we present an exploration-based trajectory optimization approach, r…
Rationale-Enhanced Language Models are Better Continual Relation Learners
Weimin Xiong, Yifan Song, Peiyi Wang +1
Continual relation extraction (CRE) aims to solve the problem of catastrophic forgetting when learning a sequence of newly emerging relations. Recent CRE studies have found that ca…
InfoCL: Alleviating Catastrophic Forgetting in Continual Text Classification from An Information Theoretic Perspective
Yifan Song, Peiyi Wang, Weimin Xiong +4
Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. We focus on continual text classification under the cl…
PoSE: Efficient Context Window Extension of LLMs via Positional Skip-wise Training
Dawei Zhu, Nan Yang, Liang Wang +4
Large Language Models (LLMs) are trained with a pre-defined context length, restricting their use in scenarios requiring long inputs. Previous efforts for adapting LLMs to a longer…
RestGPT: Connecting Large Language Models with Real-World RESTful APIs
Yifan Song, Weimin Xiong, Dawei Zhu +9
Tool-augmented large language models (LLMs) have achieved remarkable progress in tackling a broad range of tasks. However, existing methods are mainly restricted to specifically de…
RepCL: Exploring Effective Representation for Continual Text Classification
Yifan Song, Peiyi Wang, Dawei Zhu +3
Continual learning (CL) aims to constantly learn new knowledge over time while avoiding catastrophic forgetting on old tasks. In this work, we focus on continual text classificatio…
DocRED-FE: A Document-Level Fine-Grained Entity And Relation Extraction Dataset
Hongbo Wang, Weimin Xiong, Yifan Song +3
Joint entity and relation extraction (JERE) is one of the most important tasks in information extraction. However, most existing works focus on sentence-level coarse-grained JERE,…
Calibrating Factual Knowledge in Pretrained Language Models
Qingxiu Dong, Damai Dai, Yifan Song +3
Previous literature has proved that Pretrained Language Models (PLMs) can store factual knowledge. However, we find that facts stored in the PLMs are not always correct. It motivat…
Learning Robust Representations for Continual Relation Extraction via Adversarial Class Augmentation
Peiyi Wang, Yifan Song, Tianyu Liu +4
Continual relation extraction (CRE) aims to continually learn new relations from a class-incremental data stream. CRE model usually suffers from catastrophic forgetting problem, i.…