2 citations · 3 across the 18 of their papers we have counts for
19 papers
SVGFaith: A Two-Layer Meta-Evaluation of Faithfulness Metrics for Text-to-SVG Generation
Guotao Liang, Haitao Zhou, Biao Liu +6
Text-to-SVG systems are commonly evaluated by applying raster-image metrics to rasterised outputs, yet whether these scores capture fine-grained prompt faithfulness remains unclear…
Allocate Before You Embed: Adaptive Visual Input Allocation for Video Embeddings
Song Jin, Zhongtao Jiang, Chenglei Shen +5
Large-scale video retrieval requires embedding models to encode long and diverse videos under tight visual-input and inference budgets. Existing methods typically sample a small, f…
Why Multi-Step Tool-Use Reinforcement Learning Collapses and How Supervisory Signals Fix It
Yupu Hao, Zhuoran Jin, Huanxuan Liao +2
Tool use enables large language models (LLMs) to perform complex tasks, and recent agentic reinforcement learning (RL) methods show promise for enhancing model capabilities. Howeve…
Pushing the Limits of LLM Tool Calling via Experiential Knowledge Integration and Activation
Yupu Hao, Zhuoran Jin, Huanxuan Liao +2
Large language models (LLMs) rely on tool use to act as autonomous agents, yet often fail in multi-step execution due to insufficient tool-related knowledge and ineffective knowled…
ResAdapt: Adaptive Resolution for Efficient Multimodal Reasoning
Huanxuan Liao, Zhongtao Jiang, Yupu Hao +6
Multimodal Large Language Models (MLLMs) achieve stronger visual understanding by scaling input fidelity, yet the resulting visual token growth makes jointly sustaining high spatia…
Bottom-up Policy Optimization: Your Language Model Policy Secretly Contains Internal Policies
Yuqiao Tan, Minzheng Wang, Shizhu He +6
Existing reinforcement learning (RL) approaches treat large language models (LLMs) as a unified policy, overlooking their internal mechanisms. In this paper, we decompose the LLM-b…
SparK: Query-Aware Unstructured Sparsity with Recoverable KV Cache Channel Pruning
Huanxuan Liao, Yixing Xu, Shizhu He +6
Long-context inference in large language models (LLMs) is increasingly constrained by the KV cache bottleneck: memory usage grows linearly with sequence length, while attention com…
Beyond Hard and Soft: Hybrid Context Compression for Balancing Local and Global Information Retention
Huanxuan Liao, Wen Hu, Yao Xu +3
Large Language Models (LLMs) encounter significant challenges in long-sequence inference due to computational inefficiency and redundant processing, driving interest in context com…
Evaluating Personalized Tool-Augmented LLMs from the Perspectives of Personalization and Proactivity
Yupu Hao, Pengfei Cao, Zhuoran Jin +4
Personalized tool utilization is essential for aligning large language models (LLMs) with user preference in interaction scenarios with various tools. However, most of the current…
Dynamic Parametric Retrieval Augmented Generation for Test-time Knowledge Enhancement
Yuqiao Tan, Shizhu He, Huanxuan Liao +2
Retrieval-augmented generation (RAG) enhances large language models (LLMs) by retrieving relevant documents from external sources and incorporating them into the context. While it…
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…
DATA: Decomposed Attention-based Task Adaptation for Rehearsal-Free Continual Learning
Huanxuan Liao, Shizhu He, Yupu Hao +2
Continual learning (CL) is essential for Large Language Models (LLMs) to adapt to evolving real-world demands, yet they are susceptible to catastrophic forgetting (CF). While tradi…
Shuttle Between the Instructions and the Parameters of Large Language Models
Wangtao Sun, Haotian Xu, Huanxuan Liao +5
The interaction with Large Language Models (LLMs) through instructions has been extensively investigated in the research community. While instructions have been widely used as the…
CITI: Enhancing Tool Utilizing Ability in Large Language Models without Sacrificing General Performance
Yupu Hao, Pengfei Cao, Zhuoran Jin +4
Tool learning enables the Large Language Models (LLMs) to interact with the external environment by invoking tools, enriching the accuracy and capability scope of LLMs. However, pr…
Neural-Symbolic Collaborative Distillation: Advancing Small Language Models for Complex Reasoning Tasks
Huanxuan Liao, Shizhu He, Yao Xu +3
In this paper, we propose ural-mbolic ollaborative istillation (), a novel knowledge distillation method for lear…
: Internalizing Symbolic Knowledge for Distilling Better CoT Capabilities into Small Language Models
Huanxuan Liao, Shizhu He, Yupu Hao +4
Small Language Models (SLMs) are attracting attention due to the high computational demands and privacy concerns of Large Language Models (LLMs). Some studies fine-tune SLMs using…
From Instance Training to Instruction Learning: Task Adapters Generation from Instructions
Huanxuan Liao, Shizhu He, Yao Xu +5
Large language models (LLMs) have acquired the ability to solve general tasks by utilizing instruction finetuning (IFT). However, IFT still relies heavily on instance training of e…
Awakening Augmented Generation: Learning to Awaken Internal Knowledge of Large Language Models for Question Answering
Huanxuan Liao, Shizhu He, Yao Xu +4
Retrieval-Augmented-Generation and Generation-Augmented-Generation have been proposed to enhance the knowledge required for question answering with Large Language Models (LLMs) by…
LMTuner: An user-friendly and highly-integrable Training Framework for fine-tuning Large Language Models
Yixuan Weng, Zhiqi Wang, Huanxuan Liao +4
With the burgeoning development in the realm of large language models (LLMs), the demand for efficient incremental training tailored to specific industries and domains continues to…