BAIDU

company

Verified

https://www.baidu.com/

AI & ML interests

None defined yet.

Recent Activity

lingyongyan submitted a paper about 18 hours ago

DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

robingg1 new activity 1 day ago

baidu/NAVA:Please make a Comfyui workflow.

dongsheng submitted a paper 2 days ago

When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

View all activity

Papers

DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

View all Papers

Articles

Qianfan-VL: A Milestone Achievement in Chinese Multimodal AI with Domestic Chips

Unleashing the Full Potential of ERNIE4.5 using FastDeploy

PP-OCRv5 on Hugging Face: A Specialized Approach to OCR

View all articles

baidu 's papers 18

Submitted by

Lingyong Yan

DuMate-DeepResearch: An Auditable Multi-Agent System with Recursive Search and Rubric-Grounded Reasoning

baidu

Submitted by

dongsheng zhu

When Tools Fail: Benchmarking Dynamic Replanning and Anomaly Recovery in LLM Agents

baidu

Submitted by

Dong Xie

MapAgent: An Industrial-Grade Agentic Framework for City-scale Lane-level Map Generation

baidu

Submitted by

Longbin Ji

Native Audio-Visual Alignment for Generation

baidu

Submitted by

Rui Kong

Measuring Maximum Activations in Open Large Language Models

baidu

Submitted by

Rui Kong

EndPrompt: Efficient Long-Context Extension via Terminal Anchoring

baidu

Submitted by

daxiang

AEM: Adaptive Entropy Modulation for Multi-Turn Agentic Reinforcement Learning

baidu

Submitted by

HeBolei

Graph-Based Chain-of-Thought Pruning for Reducing Redundant Reflections in Reasoning LLMs

baidu

2

RefAlign: Representation Alignment for Reference-to-Video Generation

baidu

Submitted by

Yuxin Song

SAMA: Factorized Semantic Anchoring and Motion Alignment for Instruction-Guided Video Editing

baidu

Submitted by

daxiang

Qianfan-OCR: A Unified End-to-End Model for Document Intelligence

baidu

Submitted by

YijuGuo

Less Noise, More Voice: Reinforcement Learning for Reasoning via Instruction Purification

baidu

4

LoongFlow: Directed Evolutionary Search via a Cognitive Plan-Execute-Summarize Paradigm

baidu

GlobalRAG: Enhancing Global Reasoning in Multi-hop Question Answering via Reinforcement Learning

baidu

Knowledge-Level Consistency Reinforcement Learning: Dual-Fact Alignment for Long-Form Factuality

baidu

Submitted by

CYK

MA-RLHF: Reinforcement Learning from Human Feedback with Macro Actions

baidu

Tool-Augmented Reward Modeling

baidu

ERNIE-Code: Beyond English-Centric Cross-lingual Pretraining for Programming Languages

baidu