Continual Learning Mechanisms Compose for Long-Horizon Memorization Paper • 2609.06986 • Published 19 days ago • 373
Negative Self-Distillation: Learning to Reason by Avoiding Flaws Paper • 2609.11699 • Published 16 days ago • 36
SQS: Bayesian DNN Compression through Sparse Quantized Sub-distributions Paper • 2510.08999 • Published 19 days ago • 19
Compile by Training: Turning Natural-Language Specifications into Local Neural Functions Paper • 2609.04199 • Published 23 days ago • 327
Beyond Retrieval: Progressive Latent Memory Evolution for Streaming Video Understanding Paper • 2609.04131 • Published 23 days ago • 31
Knowing When Not to Reuse: Conditional Experience Transfer in Autonomous LLM Post-Training Paper • 2608.26730 • Published about 1 month ago • 155
Why Gated DeltaNet Survives 4-Bit Quantization: NVFP4 W4A4 for the Recurrent Half of a Hybrid 27B LLM Paper • 2609.04098 • Published 23 days ago • 84
Mitigating Gender Bias in English to Romanian Machine Translation Paper • 2608.08606 • Published Aug 9 • 9
FactorJEPA: Factorizing Monolithic Futures into Layout-Agent-Interaction Channels for Crowded and Chaotic Global South Urban Worlds Paper • 2608.01049 • Published Aug 2 • 13
Any-OPD: Heterogeneous On-Policy Distillation for Flow-Matching Models via Representation-Space Bridging Paper • 2608.03316 • Published Aug 4 • 26