Wei Zhang
9 papers · Latest:
Unsupervised Denoising of Real Clinical Low Dose Liver CT with Perceptual Attention Networks
An unsupervised deep learning framework with perceptual attention networks effectively denoises real clinical low-dose liver CT images.
ASPIRE: Make Spectral Graph Collaborative Filtering Great Again via Adaptive Filter Learning
ASPIRE introduces an adaptive filter learning framework for spectral graph collaborative filtering, overcoming manual tuning and "low-frequency explosion."
AutoINV: Automated Invariant Generation Framework for Formal Verification on High-Level Synthesis Designs
AutoINV is a framework that generates helper assertions from high-level synthesis designs to significantly speed up formal verification of HLS-generated hardware.
Break the Optimization Barrier of LLM-Enhanced Recommenders: A Theoretical Analysis and Practical Framework
TF-LLMER addresses optimization barriers in LLM-enhanced recommenders by normalizing embeddings and using Rec-PCA for better semantic-collaborative alignment.
A Self-Evolving Framework for Efficient Terminal Agents via Observational Context Compression
TACO is a self-evolving framework that efficiently compresses observational context for terminal agents, reducing token costs and improving performance.
From Imitation to Discrimination: Progressive Curriculum Learning for Robust Web Navigation
This paper introduces the Triton dataset and a progressive curriculum for robust web navigation, achieving SOTA performance and surpassing large LMs.
MirageBackdoor: A Stealthy Attack that Induces Think-Well-Answer-Wrong Reasoning
MirageBackdoor is a stealthy attack on LLMs that makes them think correctly but give wrong answers, bypassing current CoT defenses.
InCoder-32B-Thinking: Industrial Code World Model for Thinking
InCoder-32B-Thinking generates expert reasoning traces for industrial code by combining error-driven chain-of-thought with a hardware-aware world model.
FSUNav: A Cerebrum-Cerebellum Architecture for Fast, Safe, and Universal Zero-Shot Goal-Oriented Navigation
FSUNav introduces a cerebrum-cerebellum architecture with VLMs for fast, safe, and universal zero-shot goal-oriented navigation across diverse robots.
📬 Weekly AI Paper Digest
Get the top 10 AI/ML arXiv papers from the week — summarized, scored, and delivered to your inbox every Monday.