Does Fine-Tuning Undo Activation Steering? Behavioural Recovery Without Weight-Edit Reversal
Research
Research News
New papers, breakthroughs and academic AI research
Modality Fault Lines: Structural Corruptions Reveal Fragile Omni-Modal Reasoning
Research
CPR for LLMs: Critical-Point Routing against Catastrophic Forgetting in Domain Adaptation
Research
Beyond Compilation: Evaluating Faithful Natural-Language-to-Lean Statement Formalization
Research
FairProp: Fair Node Representation Learning via Differentiable Propagation Layers
Research
AgenticPD: A Stage-Aware Agentic Framework for Closed-Loop Physical Design Optimization
Research
WaveGSSM: Graph Wave State Space Models for Propagating Spatio-Temporal Patterns
Research
The Harness Effect: How Orchestration Design Sets the Token Economics of Enterprise Agentic AI
Research
A Fine-Grained Analysis of the LoRA Fine-Tuning Landscape with Implications for Data Selection
Research
A Hypertoroidal Covering for Perfect Color Equivariance
Research
Mastermind: Strategy-grounded Learning for Repository-Scale Vulnerability Reproduction
Research
Harnessing Multimodal Large Language Models for Training-Free Human-Object Interaction Detection
Research