Yaojie Lu
- Papers
- 22
Cite
Notes
Only stored in your browser.
Authored papers
22Beyond Text-Dominance: Understanding Modality Preference of Omni-modal Large Language Models
arXiv 2026
Decoupling Reasoning and Confidence: Resurrecting Calibration in Reinforcement Learning from Verifiable Rewards
arXiv 2026
Towards Real-world Human Behavior Simulation: Benchmarking Large Language Models on Long-horizon, Cross-scenario, Heterogeneous Behavior Traces
arXiv 2026
MetaphorVU: Towards Metaphorical Video Understanding
arXiv 2026
PPTAgent: Generating and Evaluating Presentations Beyond Text-to-Slides
arXiv 2025
ConsistentChat: Building Skeleton-Guided Consistent Dialogues for Large Language Models from Scratch
arXiv 2025
SAISA: Towards Multimodal Large Language Models with Both Training and Inference Efficiency
arXiv 2025
LiveMCPBench: Can Agents Navigate an Ocean of MCP Tools?
arXiv 2025
The Devil Is in the Details: Tackling Unimodal Spurious Correlations for Generalizable Multimodal Reward Models
arXiv 2025
ShortV: Efficient Multimodal Large Language Models by Freezing Visual Tokens in Ineffective Layers
ICCV 2025
PaperRegister: Boosting Flexible-grained Paper Search via Hierarchical Register Indexing
arXiv 2025
Cheems: A Practical Guidance for Building and Evaluating Chinese Reward Models from Scratch
arXiv 2025
DeepRAG: Thinking to Retrieval Step by Step for Large Language Models
arXiv 2025
DeepSolution: Boosting Complex Engineering Solution Design via Tree-based Exploration and Bi-point Thinking
arXiv 2025
Auto-RT: Automatic Jailbreak Strategy Exploration for Red-Teaming Large Language Models
arXiv 2025
StructRAG: Boosting Knowledge Intensive Reasoning of LLMs via Inference-time Hybrid Information Structurization
arXiv 2024
Beyond Correctness: Benchmarking Multi-dimensional Code Generation for Large Language Models
arXiv 2024
Aligning Large Language Models via Self-Steering Optimization
arXiv 2024
Self-Retrieval: End-to-End Information Retrieval with One Large Language Model
arXiv 2024
READoc: A Unified Benchmark for Realistic Document Structured Extraction
arXiv 2024
SoFA: Shielded On-the-fly Alignment via Priority Rule Following
arXiv 2024
Transferable Post-training via Inverse Value Learning
arXiv 2024
Affiliations
Frequent co-authors
10from 22 papers