Blog
No more endless PDFs. Discover the core value of the latest top-tier research in one article.
Parcae: Scaling Laws For Stable Looped Language Models
Attention to Mamba: A Recipe for Cross-Architecture Distillation
Dynamic Ranked List Truncation for Reranking Pipelines via LLM-generated Reference-Documents
Think Anywhere in Code Generation
FaithAct: Enhancing RAG Faithfulness via Learnable Activation-Guided Sparse Reinforcement Learning
ARES: An Automated Evaluation Framework for Retrieval-Augmented Generation Systems
Where is here?
Biochemistry and molecular biology of lithotrophic sulfur oxidation by taxonomically and ecologically diverse bacteria and archaea
A Mechanistic Analysis of Looped Reasoning Language Models
LACE: Lattice Attention for Cross-thread Exploration
LatentChem: From Textual CoT to Latent Thinking in Chemical Reasoning Haven
(1D) Ordered Tokens Enable Efficient Test-Time Search
RankFlow: A Multi-Role Collaborative Reranking Workflow Utilizing Large Language Models
VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck
SSMamba: A self-supervised hybrid state space model for pathological image classification.
Deliberative Searcher: Improving LLM Reliability via Reinforcement Learning with constraints
Dive into Claude Code: The Design Space of Today's and Future AI Agent Systems
Rethinking On-Policy Distillation of Large Language Models: Phenomenology, Mechanism, and Recipe
MATHNET: A GLOBAL MULTIMODAL BENCHMARK FOR MATHEMATICAL REASONING AND RETRIEVAL
Through the Lens of Core Competency: Survey on Evaluation of Large Language Models
VIB-Probe: Detecting and Mitigating Hallucinations in Vision-Language Models via Variational Information Bottleneck
Qwen3.5-Omni Technical Report
Seedance 2.0: Advancing Video Generation for World Complexity
Qwen3.5-Omni Technical Report
Towards Ultra-High-Rate Quantum Error Correction with Reconfigurable Atom Arrays
FS-Researcher: Test-Time Scaling for Long-Horizon Research Tasks with File-System-Based Agents
Empowering Multi-Turn Tool-Integrated Reasoning with Group Turn Policy Optimization
Maximizing Local Entropy Where It Matters: Prefix-Aware Localized LLM Unlearning
Scaling Test-Time Compute for Agentic Coding
Neural Garbage Collection: Learning to Forget while Learning to Reason