1 citations · 4 across the 11 of their papers we have counts for
13 papers
Evidence-Grounded Multi-Agent Planning Support for Urban Carbon Governance via RAG
Yuyan Huang, Haoran Li, Yifan Lu +3
Urban carbon governance requires planners to integrate heterogeneous evidence -- emission inventories, statistical yearbooks, policy texts, technical measures, and academic finding…
Pushing the Boundaries of Natural Reasoning: Interleaved Bonus from Formal-Logic Verification
Chuxue Cao, Jinluan Yang, Haoran Li +8
Large Language Models (LLMs) show remarkable capabilities, yet their stochastic next-token prediction creates logical inconsistencies and reward hacking that formal symbolic system…
Towards Multi-modal Multi-turn Safety: From Agentic Interaction to Strategic Alignment
Han Zhu, Jiale Chen, Chengkun Cai +8
Despite remarkable capability in multi-modal understanding, deploying Multi-modal Large Language Models (MLLMs) in open-ended conversational scenarios introduces safety risks that…
4DWorldBench: A Comprehensive Evaluation Framework for 3D/4D World Generation Models
Yiting Lu, Wei Luo, Peiyan Tu +8
World Generation Models are emerging as a cornerstone of next-generation multimodal intelligence systems. Unlike traditional 2D visual generation, World Models aim to construct rea…
SafeMT: Multi-turn Safety for Multimodal Language Models
Han Zhu, Juntao Dai, Jiaming Ji +8
With the widespread use of multi-modal Large Language models (MLLMs), safety issues have become a growing concern. Multi-turn dialogues, which are more common in everyday interacti…
StoryBox: Collaborative Multi-Agent Simulation for Hybrid Bottom-Up Long-Form Story Generation Using Large Language Models
Zehao Chen, Rong Pan, Haoran Li
Human writers often begin their stories with an overarching mental scene, where they envision the interactions between characters and their environment. Inspired by this creative p…
Semi-Supervised Synthetic Data Generation with Fine-Grained Relevance Control for Short Video Search Relevance Modeling
Haoran Li, Zhiming Su, Junyan Yao +6
Synthetic data is widely adopted in embedding models to ensure diversity in training data distributions across dimensions such as difficulty, length, and language. However, existin…
Improving the Reasoning of Multi-Image Grounding in MLLMs via Reinforcement Learning
Bob Zhang, Haoran Li, Tao Zhang +5
Multimodal Large Language Models (MLLMs) perform well in single-image visual grounding but struggle with real-world tasks that demand cross-image reasoning and multi-modal instruct…
KSOD: Knowledge Supplement for LLMs On Demand
Haoran Li, Junfeng Hu
Large Language Models (LLMs) have demonstrated remarkable capabilities in various tasks, yet still produce errors in domain-specific tasks. To further improve their performance, we…
Interpersonal Memory Matters: A New Task for Proactive Dialogue Utilizing Conversational History
Bowen Wu, Wenqing Wang, Haoran Li +3
Proactive dialogue systems aim to empower chatbots with the capability of leading conversations towards specific targets, thereby enhancing user engagement and service autonomy. Ex…
ROOT: VLM based System for Indoor Scene Understanding and Beyond
Yonghui Wang, Shi-Yong Chen, Zhenxing Zhou +4
Recently, Vision Language Models (VLMs) have experienced significant advancements, yet these models still face challenges in spatial hierarchical reasoning within indoor scenes. In…
DiffEditor: Enhancing Speech Editing with Semantic Enrichment and Acoustic Consistency
Yang Chen, Yuhang Jia, Shiwan Zhao +4
As text-based speech editing becomes increasingly prevalent, the demand for unrestricted free-text editing continues to grow. However, existing speech editing techniques encounter…
Sub-network Discovery and Soft-masking for Continual Learning of Mixed Tasks
Zixuan Ke, Bing Liu, Wenhan Xiong +2
Continual learning (CL) has two main objectives: preventing catastrophic forgetting (CF) and encouraging knowledge transfer (KT). The existing literature mainly focused on overcomi…