15 papers
From Rollouts to Recipes: Self-Contained Post-Training for LLMs
Yifei Li, Lingling Zhang, Muye Huang +3
Post-training large language models usually applies a single training recipe to all samples, even though the model's own rollouts reveal different sample-level learning states. We…
Self-Specialized Teachers for Domain Post-Training
Yifei Li, Rongman Xu, Lingling Zhang +5
Target-only post-training can improve performance in a specialized domain while degrading behaviors that a general-purpose base model acquired before adaptation. We study this prob…
Beyond Retrieval: Query-Conditioned Reuse of Long-Horizon Agent Trajectories
Yifei Li, Heng Wang, Lingling Zhang +5
Retrieval can identify a past trajectory that may matter, yet it does not specify how an acting agent should use that trajectory after users, entities, constraints, or environment…
DuplexOmni: Real-Time Listening, Seeing, Thinking, and Speaking for Full-Duplex Interaction
Muye Huang, Lingling Zhang, Xingyu Yu +7
Human interaction is continuous, multimodal, and full-duplex by nature. Although recent omni models have made substantial progress in unified speech, vision, and text modeling, com…
Visual-OPSD: Cross-Modal On-Policy Self-Distillation for Efficient Unified Multimodal Reasoning
Pengyu Li, Zhitao Gao, Lingling Zhang +5
Unified multimodal models (UMMs) interleave generated ''visual thoughts'' (VTs) with text reasoning to improve spatial tasks. This incurs roughly an order-of-magnitude inference co…
ChartAct: A Benchmark for Dynamic Chart Understanding
Muye Huang, Lin Wu, Lingling Zhang +5
Charts are widely used to present complex data for analysis and decision making. Existing chart understanding benchmarks mainly focus on static charts, but real-world charts are of…
Locomo-Plus: Beyond-Factual Cognitive Memory Evaluation Framework for LLM Agents
Yifei Li, Weidong Guo, Lingling Zhang +6
Long-term conversational memory is a core capability for LLM-based dialogue systems, yet existing benchmarks and evaluation protocols primarily focus on surface-level factual recal…
OdysseyArena: Benchmarking Large Language Models For Long-Horizon, Active and Inductive Interactions
Hang Yan, Fangzhi Xu, Qiushi Sun +14
The advancement of Large Language Models (LLMs) has catalyzed the development of autonomous agents capable of navigating complex environments. However, existing evaluations primari…
SketchVL: Policy Optimization via Fine-Grained Credit Assignment for Chart Understanding and More
Muye Huang, Lingling Zhang, Yifei Li +2
Charts are high-density visual carriers of complex data and medium for information extraction and analysis. Due to the need for precise and complex visual reasoning, automated char…
SAGE: Scale-Aware Gradual Evolution for Continual Knowledge Graph Embedding
Yifei Li, Lingling Zhang, Hang Yan +4
Traditional knowledge graph (KG) embedding methods aim to represent entities and relations in a low-dimensional space, primarily focusing on static graphs. However, real-world KGs…
ChartSketcher: Reasoning with Multimodal Feedback and Reflection for Chart Understanding
Muye Huang, Lingling Zhang, Jie Ma +6
Charts are high-density visualization carriers for complex data, serving as a crucial medium for information extraction and analysis. Automated chart understanding poses significan…
Diagram-Driven Course Questions Generation
Xinyu Zhang, Lingling Zhang, Yanrui Wu +6
Visual Question Generation (VQG) research focuses predominantly on natural images while neglecting the diagram, which is a critical component in educational materials. To meet the…
GoT-CQA: Graph-of-Thought Guided Compositional Reasoning for Chart Question Answering
Lingling Zhang, Muye Huang, QianYing Wang +3
Chart Question Answering (CQA) aims at answering questions based on the visual chart content, which plays an important role in chart sumarization, business data analysis, and data…
VProChart: Answering Chart Question through Visual Perception Alignment Agent and Programmatic Solution Reasoning
Muye Huang, Lingling Zhang, Lai Han +3
Charts are widely used for data visualization across various fields, including education, research, and business. Chart Question Answering (CQA) is an emerging task focused on the…
EvoChart: A Benchmark and a Self-Training Approach Towards Real-World Chart Understanding
Muye Huang, Han Lai, Xinyu Zhang +4
Chart understanding enables automated data analysis for humans, which requires models to achieve highly accurate visual comprehension. While existing Visual Language Models (VLMs)…