Haobo Wang

Stop Unnecessary Reflection: Training LRMs for Efficient Reasoning with Adaptive Reflection and Length Coordinated Penalty

FLoE: Fisher-Based Layer Selection for Efficient Sparse Adaptation of Low-Rank Experts

TraPO: A Semi-Supervised Reinforcement Learning Framework for Boosting LLM Reasoning

Tensorized Multi-View Multi-Label Classification via Laplace Tensor Rank

Representation Surgery in Model Merging with Probabilistic Modeling

Table as a Modality for Large Language Models

Harnessing Feature Resonance under Arbitrary Target Alignment for Out-of-Distribution Node Detection

Mitigating Local Cohesion and Global Sparseness in Graph Contrastive Learning with Fuzzy Boundaries

Steer LLM Latents for Hallucination Detection

Bridging the Semantic Gap Between Text and Table: A Case Study on NL2SQL

Automatic Dataset Construction (ADC): Sample Collection, Data Curation, and Beyond

Defending Multimodal Backdoored Models by Repulsive Visual Prompt Tuning

Injecting Learnable Table Features into LLMs

Enhance Multi-View Classification Through Multi-Scale Alignment and Expanded Boundary

FedSR: Frequency-Aware Enhancement for Diffusion-based Image Super-Resolution