DeepSeek-V3.2: Pushing the Frontier of Open Large Language Models
Paper • 2512.02556 • Published • 274
Check out later
-
-
Skywork-R1V4: Toward Agentic Multimodal Intelligence through Interleaved Thinking with Images and DeepResearch
Paper • 2512.02395 • Published • 52 -
Deep Research: A Systematic Survey
Paper • 2512.02038 • Published • 73 -
How Far Are We from Genuinely Useful Deep Research Agents?
Paper • 2512.01948 • Published • 58 -
Benchmarking Knowledge-Extraction Attack and Defense on Retrieval-Augmented Generation
Paper • 2602.09319 • Published • 1 -
Exploring Spatial Intelligence from a Generative Perspective
Paper • 2604.20570 • Published • 22 -
Look Light, Think Heavy: What Multimodal Chain-of-Thought Reasoning Can and Cannot Do
Paper • 2606.22565 • Published • 9 -
Thought-Level Beam Search for Reasoning
Paper • 2608.08020 • Published • 16 -
HarnessDev: Can LLMs Create and Evolve Their Own Agent Harness?
Paper • 2609.01437 • Published • 516 -
OpenWAM: An Open, Modular Exploration Towards Systematic World-Action Model Pretraining
Paper • 2609.07398 • Published • 80 -
NCP-ArchPreview Technical Report: Moving towards Latent Space Language Models through Next Concept Prediction
Paper • 2609.10715 • Published • 268 -
Geometry of Values: Task Vector Composition for Ethical Preference Alignment in Language Models
Paper • 2609.21094 • Published • 6 -
The Evolution of Attention in Large Language Models: Mechanisms, Trade-offs, and Emerging Trends
Paper • 2609.39661 • Published • 13 -
BiasReducer: Adaptive Bias Mitigation for Reward Models
Paper • 2609.32720 • Published • 27 -
Does Learning Protein Folding Generalize to Broader Reasoning?
Paper • 2609.38879 • Published • 63 -
Learning Functional Subspaces for Neural Network Compression
Paper • 2609.40127 • Published • 25