-
Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
Paper • 2512.24617 • Published • 66 -
Recursive Language Models
Paper • 2512.24601 • Published • 94 -
Nested Learning: The Illusion of Deep Learning Architectures
Paper • 2512.24695 • Published • 45 -
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
Paper • 2512.02556 • Published • 265
Collections
Discover the best community collections!
Collections including paper arxiv:2502.11089
-
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 170 -
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 145 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 447 -
DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning
Paper • 2504.07128 • Published • 87
-
Large Language Diffusion Models
Paper • 2502.09992 • Published • 127 -
MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
Paper • 2502.10391 • Published • 34 -
Diverse Inference and Verification for Advanced Reasoning
Paper • 2502.09955 • Published • 18 -
Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models
Paper • 2502.08130 • Published • 9
-
Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
Paper • 2412.06531 • Published • 72 -
Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents
Paper • 2309.17207 • Published -
Titans: Learning to Memorize at Test Time
Paper • 2501.00663 • Published • 31 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 170
-
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
Paper • 2502.08910 • Published • 150 -
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity
Paper • 2502.13063 • Published • 74 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 170 -
LLM Pretraining with Continuous Concepts
Paper • 2502.08524 • Published • 30
-
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Paper • 2310.16818 • Published • 33 -
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
Paper • 2401.02954 • Published • 55 -
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Paper • 2401.06066 • Published • 61 -
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
Paper • 2401.14196 • Published • 72
-
ReLearn: Unlearning via Learning for Large Language Models
Paper • 2502.11190 • Published • 30 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 170 -
Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
Paper • 2502.11357 • Published • 11 -
DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding
Paper • 2503.12797 • Published • 32
-
Dynamic Large Concept Models: Latent Reasoning in an Adaptive Semantic Space
Paper • 2512.24617 • Published • 66 -
Recursive Language Models
Paper • 2512.24601 • Published • 94 -
Nested Learning: The Illusion of Deep Learning Architectures
Paper • 2512.24695 • Published • 45 -
DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
Paper • 2512.02556 • Published • 265
-
DreamCraft3D: Hierarchical 3D Generation with Bootstrapped Diffusion Prior
Paper • 2310.16818 • Published • 33 -
DeepSeek LLM: Scaling Open-Source Language Models with Longtermism
Paper • 2401.02954 • Published • 55 -
DeepSeekMoE: Towards Ultimate Expert Specialization in Mixture-of-Experts Language Models
Paper • 2401.06066 • Published • 61 -
DeepSeek-Coder: When the Large Language Model Meets Programming -- The Rise of Code Intelligence
Paper • 2401.14196 • Published • 72
-
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 170 -
DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language Models
Paper • 2402.03300 • Published • 145 -
DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement Learning
Paper • 2501.12948 • Published • 447 -
DeepSeek-R1 Thoughtology: Let's <think> about LLM Reasoning
Paper • 2504.07128 • Published • 87
-
Large Language Diffusion Models
Paper • 2502.09992 • Published • 127 -
MM-RLHF: The Next Step Forward in Multimodal LLM Alignment
Paper • 2502.10391 • Published • 34 -
Diverse Inference and Verification for Advanced Reasoning
Paper • 2502.09955 • Published • 18 -
Selective Self-to-Supervised Fine-Tuning for Generalization in Large Language Models
Paper • 2502.08130 • Published • 9
-
Unraveling the Complexity of Memory in RL Agents: an Approach for Classification and Evaluation
Paper • 2412.06531 • Published • 72 -
Memory Gym: Towards Endless Tasks to Benchmark Memory Capabilities of Agents
Paper • 2309.17207 • Published -
Titans: Learning to Memorize at Test Time
Paper • 2501.00663 • Published • 31 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 170
-
InfiniteHiP: Extending Language Model Context Up to 3 Million Tokens on a Single GPU
Paper • 2502.08910 • Published • 150 -
Cramming 1568 Tokens into a Single Vector and Back Again: Exploring the Limits of Embedding Space Capacity
Paper • 2502.13063 • Published • 74 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 170 -
LLM Pretraining with Continuous Concepts
Paper • 2502.08524 • Published • 30
-
ReLearn: Unlearning via Learning for Large Language Models
Paper • 2502.11190 • Published • 30 -
Native Sparse Attention: Hardware-Aligned and Natively Trainable Sparse Attention
Paper • 2502.11089 • Published • 170 -
Explorer: Scaling Exploration-driven Web Trajectory Synthesis for Multimodal Web Agents
Paper • 2502.11357 • Published • 11 -
DeepPerception: Advancing R1-like Cognitive Visual Perception in MLLMs for Knowledge-Intensive Visual Grounding
Paper • 2503.12797 • Published • 32