Wei Wang
9 papers · Latest:
Quality-Aware Collaborative Multi-Positive Contrastive Learning for Sequential Recommendation
QCMP-CL introduces quality-aware collaborative multi-positive contrastive learning for sequential recommendation, improving view diversity and consistency.
DGPO: Beyond Pairwise Preferences with Directional Consistent Groupwise Optimization
DGPO is a new preference optimization method for LLMs that improves directional consistency and reasoning diversity using group-wise, multi-candidate comparisons.
SphereVAD: Training-Free Video Anomaly Detection via Geodesic Inference on the Unit Hypersphere
SphereVAD offers training-free video anomaly detection by leveraging pre-trained MLLM features and geometric inference on a unit hypersphere.
FitText: Evolving Agent Tool Ecologies via Memetic Retrieval
FitText introduces a training-free framework that dynamically evolves agent tool retrieval by generating and refining pseudo-tool descriptions using memetic retrieval.
Crab: A Semantics-Aware Checkpoint/Restore Runtime for Agent Sandboxes
Crab is a runtime that bridges the agent-OS semantic gap for efficient and correct checkpoint/restore in agent sandboxes.
Learning to Reason with Insight for Informal Theorem Proving
A new framework and dataset enable LLMs to perform insightful informal theorem proving by learning to recognize core techniques.
Divergence of detachment forces in the finite Voronoi model
This paper analyzes the finite Voronoi model, revealing divergent detachment forces that cause time-step dependence in fracture simulations and proposing a regularization.
Well Begun is Half Done: Training-Free and Model-Agnostic Semantically Guaranteed User Representation Initialization for Multimodal Recommendation
This paper introduces SG-URInit, a training-free and model-agnostic method to initialize semantically rich user representations for multimodal recommendation systems.
Qwen Technical Report
Qwen is a versatile large language model series featuring base, chat, coding, and math-specialized models that achieve strong performance across diverse AI tasks, rivaling larger and proprietary models.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.