The feed — everything that cleared the gates

Signal over volume.

668 articles · every one names its model and score

All Molecular biology Biology Neuroscience Medicine Engineering AI/ML Mathematics Chemistry Psychology Physics Social science

sort / newest score

505

AI/ML Jun 03, 2026 5 min

Beyond Encoder Accumulation: Rethinking Multi-Encoder Design in Vision-Langua...

Beyond Encoder Accumulation: Rethinking Multi-Encoder Design in Vision-Language Models

8.0/10 read

506

AI/ML Jun 03, 2026 6 min

Beyond Accuracy: Measuring the Structural Efficiency of LLM Reasoning via Cla...

Beyond Accuracy: Measuring the Structural Efficiency of LLM Reasoning via Claim Graphs

8.0/10 read

507

AI/ML Jun 03, 2026 5 min

MindZero: Training MLLMs for Real-Time Theory of Mind via Self-Supervised Rei...

8.6/10 read

508

AI/ML Jun 03, 2026 5 min

TELL: Moving AI Text Detection from Opaque Scores to Human-Centric Explanations

8.6/10 read

509

AI/ML Jun 03, 2026 5 min

X-Stream: The First Benchmark for Multi-Stream Streaming Video Understanding

8.3/10 read

510

AI/ML Jun 03, 2026 5 min

RoboStressBench: A Principled Framework for Evaluating VLM Robustness to Phys...

8.0/10 read

511

Engineering Jun 03, 2026 5 min

AFUN: A Foundation Model for Predicting Where and How to Interact with Objects

8.7/10 read

512

AI/ML Jun 03, 2026 6 min

SVI-Bench: Bridging the Gap from Video Perception to Strategic Agency

8.7/10 read

513

Physics Jun 03, 2026 5 min

FreeForm: Fast and Accurate Mesh-Free Reduced-Order Deformable Simulation

8.7/10 read

514

AI/ML Jun 03, 2026 5 min

DOT-MoE: Transforming Dense LLMs into Efficient Sparse Experts via Optimal Tr...

8.7/10 read

515

Engineering Jun 03, 2026 5 min

TVRBench: Bridging the Gap in Active Spatial Intelligence for Foundation Models

8.3/10 read

516

AI/ML Jun 03, 2026 5 min

VLM-as-Teacher: A New Paradigm for Adaptive Video Reasoning via Test-Time Opt...

8.3/10 read

517

Physics Jun 03, 2026 6 min

Spectral Audit: A New Diagnostic for In-Context Operator Learning Fidelity

8.7/10 read

518

AI/ML Jun 03, 2026 5 min

NITP: Enhancing LLM Pre-training via Next Implicit Token Prediction

8.3/10 read

519

AI/ML Jun 03, 2026 5 min

ODTQA-FoRe: A New Benchmark for Open-Domain Tabular QA with Future Forecasting

8.0/10 read

520

Engineering Jun 03, 2026 5 min

StreamChar: Real-Time Long-Horizon Streaming Audio-Video Generation

8.3/10 read

521

AI/ML Jun 03, 2026 5 min

K-BROWSECOMP: A New Benchmark for Korean-Context Web Browsing Agents

8.3/10 read

522

Mathematics Jun 03, 2026 6 min

Not All Errors Are Equal: Systematic Study of Error Propagation in LLM Inference

8.7/10 read

523

Molecular biology Jun 03, 2026 5 min

SMArT: A New Strategy to Purify and Enhance Precision Gene Editing in Stem Cells

8.7/10 read

524

AI/ML Jun 03, 2026 5 min

Beyond Correctness: Auditing Source-Dependence in Multi-Source Medical RAG Sy...

8.3/10 read

525

Engineering Jun 03, 2026 5 min

τ0-WM: A Unified Video-Action World Model for Robust Robotic Manipulation

8.0/10 read

526

AI/ML Jun 03, 2026 5 min

Linear Ensembles Wash Away Watermarks: The Fundamental Fragility of AI Attrib...

8.7/10 read

527

AI/ML Jun 03, 2026 6 min

Beyond Text: Introducing VISUAL SKILL for Multimodal Agent Capability

8.0/10 read

528

AI/ML Jun 03, 2026 5 min

SOCO: A New Taxonomy-Driven Benchmark for Semantic Object Correspondence

8.7/10 read