GraphToxin: Reconstructing Full Unlearned Graphs from Graph Unlearning
Research
Research News
New papers, breakthroughs and academic AI research
ResidualKV: Residual-Based KV Cache Compression for Efficient Long-Context Inference
Research
D$^2$-VLA: Dual-Memory Dual-Frequency Vision-Language-Action Model For Long Dynamic Manipulation
Research
TTLab at Daleel 2026: STAR-Ar, Sequence Tagging for Argument Recognition in Arabic
Research
Candidate Retention for Abductive Learning
Research
Self-Spec Verifiable Code Generation
Research
PISCO: Precise Video Instance Insertion with Sparse Control
Research
Frozen Memory Is Not Enough: Rethinking External Memory as Extraction
Research
Understanding Head Geometry and Dynamics in Federated Regression through a Natural Solution Selection Rule: An Unconstrained Feature Model Analysis
Research
Also Small Models Can Reasonably Self-Evaluate Their Confidence
Research
IROH: Insightful Ranking Of Humor using Multi-Stage Hybrid Retrieval with Rationale-Distilled LLM Judges for JOKER 2026 Track Task 1 English
Research
Learning Reliable GUI Agents under Imperfect Priors
Research