CNet: A Complex-Valued Deep Learning Framework with Wirtinger Autodifferentiation and FFT--Hadamard Convolution
Research
Research News
New papers, breakthroughs and academic AI research
Algorithm Selection with Zero Domain Knowledge via Text Embeddings
Research
When Attention Closes: How LLMs Lose the Thread in Multi-Turn Interaction
Research
Coding with "Enemy": Can Human Developers Detect AI Agent Sabotage?
Research
Refusal-Gated Decoding: Preserving Refusal Behavior Under High-Temperature Sampling
Research
Random Feature Gaussian Process Attention: Linear-Time Probabilistic Attention with Calibrated Uncertainty
Research
Multi-Label Perceptual Bug Detection in Video Games using Deep Learning on Gameplay Footage
Research
SubtleMemory: A Benchmark for Fine-Grained Relational Memory Discrimination in Long-Horizon AI Agents
Research
Rethinking Adapter Placement: A Dominant Adaptation Module Perspective
Research
Reinforcement Learning over Predictive Distributions for LLM Regression
Research
Early Memory Selection for Balanced Adam
Research
Seeing Isn't Knowing: Do VLMs Know When Not to Answer Spatial Questions (and Why)?
Research