Harmful SFT Leaves a Continuous Trace in LLM Checkpoint Updates
Research
Research News
New papers, breakthroughs and academic AI research
SpecBraM: What Should an EEG Foundation Model Predict? Masked Band-Power Prediction versus Waveform Reconstruction
Research
Smart Content Ingestion for Generative AI Workloads
Research
Forecasting the Growth of Social Media Information Cascades: Towards Human-in-the-Loop Misinformation Triage
Research
Activation Denoising: A Robustness View on Parallel vs Sequential LLM Quantization
Research
Responsible Institutional Analytics: Interpreting Bias with AI Support
Research
Lineage-Aware Memory Governance: A Derivation-Gated Framework for Privacy-Preserving Column-Level Access Control in Enterprise AI Agents
Research
Digital Twin-Driven Real2Sim2Real: Simulator-Conditioned Generation via Paired Driving-Scene Reconstruction
Research
DIPrune: Task-Aware Token Pruning with Dual Importance for Efficient Multimodal Language Models
Research
Which and When to Admit: Gradient Admission for Data-Centric Small Language Model Finetuning
Research
Image Bitstream Fine-grained Understanding for Privacy-Friendly AIoT
Research
PolarScale: A Physics-Grounded Benchmark for Radiometrically Consistent RGB-to-Stokes Estimation
Research