Eraser: Jailbreaking Defense in Large Language Models via Unlearning Harmful Knowledge
Research
Research News
New papers, breakthroughs and academic AI research
Authorship identification under domain shift: a survey of stylistic measures and learned author representations
Research
Compact Low-Cost Hyperspectral Imaging via Angular-to-Spectral Diversity Conversion
Research
Which Terrain Is Better? Preference Learning with VLM Prototypes for Off-Road Traversability Ranking
Research
Universal Multi-Modal Traceformer: Integrating Heterogeneous Context for Process Event Prediction
Research
$t_0$: A Time-Series Foundation Model for Forecasting with Context
Research
A Temporal Knowledge Graph for Music Festival Lineup Forecasting
Research
GAE: Learning a Geometry-Native Latent Space for 3D-Consistent World Generation
Research
Optimizers for Diffusion Models: A Controlled Benchmark
Research
Neural Spectral Capacity: Measuring and Designing Architectures from Network Specification Alone
Research
RPMem: Learning Long-Term Recurrent Parametric Memory Across Sessions for LLM Agents
Research
BabelArena: A Large-Scale Multilingual Benchmark for LLM Agents
Research