Ji-Rong Wen

VideoExplorer: Advancing Long-Horizon Video Understanding via Hierarchical Orchestration

Huaying Yuan, Zheng Liu, Junjie Zhou, Hongjin Qian et autres

Current agentic frameworks for Long-Video Understanding (LVU) remain limited by two critical problems: ineffective control, where traditional monolithic agents struggle with high-branching, multi-granularity decision processes; and inefficient supervision, where sparse, outcome-based feedback fails to guide long-horizon reasoning. To resolve these challenges, we …

cn, it (code pays fourni par la source)

SUDER: Self-Improving Unified Large Multimodal Models for Understanding and Generation with Dual Self-rewards

Yiran Zhang, Guanzhong Wang, Yi Liu, Ji-Rong Wen et autres

Building upon large language models (LLMs), recent large multimodal models (LMMs) unify cross-model understanding and generation into a single framework. However, LMMs still struggle to achieve accurate vision-language alignment, prone to generating text responses contradicting the visual input or failing to follow …

cn (code pays fourni par la source)

A Survey of Large Language Models

Wayne Xin Zhao, Kun Zhou, Junyi Li, Tianyi Tang et autres

Abstract The rapid evolution of large language models (LLMs) has driven a transformative shift in artificial intelligence (AI), reshaping both research paradigms and practical applications. Distinguished from their predecessors by unprecedented scale and advanced capabilities, LLMs necessitate new frameworks for understanding their …

cn, ca (code pays fourni par la source)

Siamese foundation models for crystal structure prediction

Li‐Ming Wu, Wenbing Huang, Liwei Liu, Yipeng Zhou et autres

Abstract Predicting crystal structures from chemical compositions is a fundamental challenge in materials discovery, complicated by complex 3D geometries that distinguish it from fields like protein folding. Here, we present Diffusion-based crystAl Omni (DAO), a pretrain-finetune framework for crystal structure prediction integrating …

cn (code pays fourni par la source)

DeepAgent: A General Reasoning Agent with Scalable Toolsets

Xiaoxi Li, Wenxiang Jiao, Jiarui Jin, Guanting Dong et autres

cn (code pays fourni par la source)

Toward Generalized Web Agent Training: A Deep Dive into Entropy-Balanced Reinforcement Learning

Guanting Dong, Licheng Bao, Kangzhi Zhao, Xiaoxi Li et autres

cn (code pays fourni par la source)

Content Generation for Information Retrieval Systems: A Survey from the Supply-Side Optimization Perspective

Xiaopeng Ye, Zhuoyang Li, 袁保松, Chen Xu et autres

cn (code pays fourni par la source)

LLaDA2.0: Scaling Up Diffusion Language Models to 100B

Tiwei Bie, Kun Chen, Liang Du, Mengyan Gong et autres

This paper presents LLaDA2.0 -- a tuple of discrete diffusion large language models (dLLM) scaling up to 100B total parameters through systematic conversion from auto-regressive (AR) models -- establishing a new paradigm for frontier-scale deployment. Instead of costly training from scratch, LLaDA2.0 …

Discovering physical laws with parallel symbolic enumeration

Kai Ruan, Yilong Xu, Ze-Feng Gao, Yang Liu et autres

Symbolic regression has a crucial role in modern scientific research owing to its capability of discovering concise and interpretable mathematical expressions from data. A key challenge lies in the search for parsimonious and generalizable mathematical formulas, in an infinite search space, while …

cn, hk (code pays fourni par la source)

How Do Large Language Models Understand Relevance? A Mechanistic Interpretability Perspective

Qi Liu, Haozhe Duan, Jiaxin Mao, Ji-Rong Wen

Recent studies have shown that large language models (LLMs) can assess relevance and support information retrieval (IR) tasks such as document ranking and relevance judgment generation. However, the internal mechanisms by which off-the-shelf LLMs understand and operationalize relevance remain largely unexplored. In …

cn (code pays fourni par la source)

DIVAgent: A Diversified Search Agent that Mimics the Human Search Process

Zhirui Deng, Jingfen Qiao, Zhicheng Dou, Ji-Rong Wen et autres

Search result diversification plays a crucial role in addressing query ambiguity and multi-faceted information needs by reducing redundancy across documents. While previous supervised approaches can achieve superior performance, they require costly, large-scale annotated data. In contrast, unsupervised methods are more flexible and …

cn, nl (code pays fourni par la source)

Addressing Personalized Bias for Unbiased Learning to Rank

Zechun Niu, Lang Mei, Liu Yang, Ziyuan Zhao et autres

Unbiased learning to rank (ULTR), which aims to learn unbiased ranking models from biased user behavior logs, plays an important role in Web search. Previous research on ULTR has studied a variety of biases in users' clicks, such as position bias, presentation …

cn (code pays fourni par la source)