Hao Liang
- Papers
- 25
Cite
Notes
Only stored in your browser.
Authored papers
25DataFlex: A Unified Framework for Data-Centric Dynamic Training of Large Language Models
arXiv 2026
One-Eval: An Agentic System for Automated and Traceable LLM Evaluation
arXiv 2026
LatentOmni: Rethinking Omni-Modal Understanding via Unified Audio-Visual Latent Reasoning
arXiv 2026
OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
arXiv 2026
VABench: A Comprehensive Benchmark for Audio-Video Generation
arXiv 2025
DataFlow: An LLM-Driven Framework for Unified Data Preparation and Workflow Automation in the Era of Data-Centric AI
arXiv 2025
MM-Verify: Enhancing Multimodal Reasoning with Chain-of-Thought Verification
arXiv 2025
Learning What Reinforcement Learning Can't: Interleaved Online Fine-Tuning for Hardest Questions
arXiv 2025
LoVR: A Benchmark for Long Video Retrieval in Multimodal Contexts
arXiv 2025
Scone: Bridging Composition and Distinction in Subject-Driven Image Generation via Unified Understanding-Generation Modeling
arXiv 2025
MorphoBench: A Benchmark with Difficulty Adaptive to Model Reasoning
arXiv 2025
Multimodal Reasoning for Science: Technical Report and 1st Place Solution to the ICML 2025 SeePhys Challenge
arXiv 2025
VCU-Bridge: Hierarchical Visual Connotation Understanding via Semantic Bridging
arXiv 2025
Let's Verify Math Questions Step by Step
arXiv 2025
FlipVQA-Miner: Cross-Page Visual Question-Answer Mining from Textbooks
arXiv 2025
Baichuan-Omni-1.5 Technical Report
arXiv 2025
CFBench: A Comprehensive Constraints-Following Benchmark for LLMs
arXiv 2024
MC-LLaVA: Multi-Concept Personalized Vision-Language Model
arXiv 2024
SynthVLM: High-Efficiency and High-Quality Synthetic Data for Vision Language Models
arXiv 2024
BEATS: Optimizing LLM Mathematical Capabilities with BackVerify and Adaptive Disambiguate based Efficient Tree Search
arXiv 2024
MathScape: Evaluating MLLMs in multimodal Math Scenarios through a Hierarchical Benchmark
arXiv 2024
QAEncoder: Towards Aligned Representation Learning in Question Answering System
arXiv 2024
Facilitating Multi-turn Function Calling for LLMs via Compositional Instruction Tuning
arXiv 2024
Synth-Empathy: Towards High-Quality Synthetic Empathy Data
arXiv 2024
Medical MLLM is Vulnerable: Cross-Modality Jailbreak and Mismatched Attacks on Medical Multimodal Large Language Models
arXiv 2024
Affiliations
Frequent co-authors
10from 25 papers