Beyond Forgetting: Representation Misdirection Elicits Controllable Side Behaviors and Capabilities
Research
Research News
New papers, breakthroughs and academic AI research
Rethinking Diffusion Segmentation: When Does It Rely on Its Noisy State, and Does Diffusion Matter?
Research
FLARE: A Full-Lifecycle Dense Supervision Paradigm for Long-Horizon Coding Agents via Generative Reward Model
Research
From UNDRR Reports to Event Records: Schema-Constrained LLM Extraction of Georeferenced Disasters
Research
Q-TIE: A Lightweight and Generalizable Re-ranking Framework for Temporal Information Retrieval
Research
A Patient World Model for Early Forecasting of Digital Health Campaign Outcomes: Capabilities and Limits
Research
ULF-Synth: Physics-Guided Ultra-Low-Field MRI Enhancement for Pediatric Neuroimaging
Research
CTRL: Control-Based Time Series Forecasting with LLM-Guided Residual Learning
Research
InterHier: Learning Interconnected Hierarchical Semantics for Open-Vocabulary Object Detection
Research
U-PEN Mamba: Progressive Expansion with Selective State-Space Modeling for Efficient Retinal Vessel Segmentation
Research
Rethinking Class Imbalance for Single-Cell Foundation Models: A Systematic Benchmark Across Architectures and Long-Tail Loss Functions
Research
Circuit Hypernetworks for Quantum-Augmented Diffusion Language Models
Research