MongoDB - Build AI That Scales
Mini toolsPapers
Filter by company
-
Mashup Learning: Faster Finetuning by Remixing Past Checkpoints
-
AI+HW 2035: Shaping the Next DecadeNVIDIA, Google, AMD, IBM, Together AI, OpenAI, SEMRON, EnCharge AI, SambaNova, SK Hynix, Oracle / Agentrys, Brown University, California Institute of Technology, Carnegie Mellon University, Hewlett Packard Labs, New York University, Princeton University, Stanford University, University at Buffalo, University of California, University of Illinois Urbana-Champaign, University of Pennsylvania, University of Texas
-
FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling
-
FlashAttention-4: Algorithm and Kernel Pipelining Co-Design for Asymmetric Hardware Scaling
-
V1 : Unifying Generation and Self-Verification for Parallel Reasoners
-
Speculative Speculative Decoding
-
Learning to Discover at Test Time
-
Asynchronous Reasoning: Training-Free Interactive Thinking LLMs
-
DSGym: A Holistic Framework for Evaluating and Training Data Science Agents
-
Understanding and Steering the Cognitive Behaviors of Reasoning Models at Test-Time
-
MagicDec: Breaking the Latency-Throughput Tradeoff for Long Context Generation with Speculative Decoding
-
RedPajama: an Open Dataset for Training Large Language Models
