Fisher-Guided Submodular Data Selection for Continual Pre-Training of Large Language Models
Research
Research News
New papers, breakthroughs and academic AI research
Activation Sparsity with Weight Approximation for Faster LLM Decoding on Offloaded Weights
Research
LEAP: Learning Efficient Action Proposals For LLM Agents
Research
Adaptive Second-Order Solvers for Fast Stochastic Diffusion Sampling
Research
Consecutive Posterior Fusion for Diffusive Recovery of Unobservable Image Structures
Research
Dense Mixture-of-Experts as a Reparameterized Wide FFN: A Granularity Sweep at Fixed Compute
Research
SEDIMA: Cross-Run Hierarchical Insight Memory for Evolutionary Search Agents
Research
T3lescope: Arbitrary-Resolution High-Fidelity Generative Surface Reconstruction from Images
Research
Evaluating and Improving the Robustness of Large Language Models to Input Sequence Variations
Research
SecJev: Bringing Security Expertise to System One Decision Models
Research
Moving Forward with Video Saliency: A New Dataset and Benchmark where Motion Matters
Research
Budgeted Cache Repair for Cross-Context KV-Cache Reuse
Research