CHANNEL

Research

"Research" is a topic channel on AGI Hunt, an AI news site updated around the clock in real time. Coverage: Papers, new methods, empirical findings, technical and research reports, academia (incl. AI4Science); benchmark and dataset releases land here.

Daily roundup: the latest AI News Daily — the past 24 hours across the whole site, per channel and per company · browse the archive

• Author publicly seeks emergency ICLR reviewers for three papers — _onionesque · 2026-10-26
• Cohere Labs' CulturalRiddles: top AI model hits 79%, some cultures just 22% — Cohere_Labs · 2026-10-26
• Cambridge NLIP brings 8 papers to EMNLP 2026, from tokenization to LLM agents — vlachos_nlp · 2026-10-26
• Context Bombs: Decoy Defenses Multiply AI Agent Attack Costs 23x — tracebit · 2026-10-26(2 related)
• Why tiny encoders hold up: multi-vector retrieval trades storage for quality — tomaarsen · 2026-10-26
• MoEdernColBERT Breakdown: MoE Retrieval Model Hits 300x Qwen3 Throughput — tomaarsen · 2026-10-26(2 related)
• V-Rubrics and EgoTools accepted to EMNLP 2026: rubric-based RL and egocentric tool reasoning — liuziwei7 · 2026-10-26
• Microduck team publishes deep dives: relocalizes within 2cm using a 64-pixel depth sensor — mishig25 · 2026-10-26
• Claude ran an introspection experiment on itself and hit 11 of 13 self-predictions — Majestic_Door_4528 · 2026-10-26
• Particle-collision pretraining cuts cosmology training data to 100 simulations — bravo_abad · 2026-10-26
• DeepSeek open model changed answers on 51 of 1,273 medical questions — thinking 12x longer and half wrong — MaziyarPanahi · 2026-10-26
• End of the turbulence thread: turbulence is (3+1)-dimensional and the time component is essential — jo_brandstetter · 2026-10-26
• New paper: 28TB time-resolved DNS shows turbulence must be treated as 4D phenomenon — jo_brandstetter · 2026-10-26
• Grid, precision and filtering choices reshape what turbulence simulations look like — jo_brandstetter · 2026-10-26
• Close-up of turbulence: thin structures carried, bent and stretched over time — jo_brandstetter · 2026-10-26
• Tennekes' 1975 Sweeping Hypothesis Explains Turbulence Time Scaling — jo_brandstetter · 2026-10-26(2 related)
• Statistical Rulers of Turbulence: From Kolmogorov's Energy Spectrum to Time Correlations — jo_brandstetter · 2026-10-26(2 related)
• (3+1)-Dimensional Turbulence: Watching Vortices Evolve in Space-Time — jo_brandstetter · 2026-10-26(2 related)
• From Reynolds' Spark-Lit Experiment to the Internal Battle in the Navier-Stokes Equations — jo_brandstetter · 2026-10-26(2 related)
• Turbulence thread: the convection–viscosity competition inside the Navier–Stokes equations — jo_brandstetter · 2026-10-26
• Numerical Choices Deeply Shape Turbulence Simulation and AI Training Data — jo_brandstetter · 2026-10-26(2 related)
• Robot runs a video generation model as its policy: frozen FLUX beats VLAs — lukas_m_ziegler · 2026-10-26
• RoboJudge: 800 human-annotated videos benchmark MLLM judges for embodied video generation — CUHK-CSE · 2026-10-26
• libgnss++: open-source C++20 GNSS toolkit recreates GPS drift in 3D Tokyo model vs RTKLIB — rsasaki0109 · 2026-10-26
• Berkeley Generates RL Policies with Diffusion Models for Real Robot Skills — FinanceYF5 · 2026-10-26(2 related)
• Anthropic Researcher: Unchecked Evaluations Just Fit Benchmark Noise — antoine_chaffin · 2026-10-26(2 related)
• Judea Pearl boosts Oregon State PhD opening at causal inference × AI intersection — yudapearl · 2026-10-26
• davidad digs into 'dynamical-systems attractor-structure functionalism' via Conley index theory — davidad · 2026-10-26
• Sakana AI hosts Tokyo RSI symposium: AI Scientist in Nature, Schmidhuber keynotes — RobertTLange · 2026-10-26
• HuggingFace's Carbon-X Spots Pathogenic Splice Variant Where Gemini 3.8 Flash Misreads the Gene — LoubnaBenAllal1 · 2026-10-26
• ETH Zurich paper: dynamic evaluation allocation matches 10x-budget model rankings — zouharvi · 2026-10-26
• TenetBench: Clause-Anchored Benchmark Finds LLMs Frequently Violate Ethics Codes — Yegor Anichkov · 2026-10-26
• DISC Learns to Combine Time-Series Dataset Similarity Metrics for Transfer Prediction — Yen-Ku Liu · 2026-10-26
• DuoLM: Fast LLM-Based Personalized Recommendation via Compact Encoder-Ranker — GoogleDeepMind · 2026-10-26
• Adobe's SliderEdit++ Improves Slider-Based Image Editing by 18.5% with New SlideBench — Arman Zarei · 2026-10-26
• DeepMind Builds Auditable AI Text Detectors with Sparse Autoencoders — GoogleDeepMind · 2026-10-26
• Google Paper: Data-Free On-Policy Self-Training Improves LLMs Across Text and Vision — google · 2026-10-26
• CoRE Framework Learns Rule Routing for Knowledge Retrieval Without Supervision — Zhisheng Qi · 2026-10-26
• Organ-Agents: 9 Organ LLM Agents Simulate 22,689 ICU Patients for Treatment Testing — mikeflache · 2026-10-26
• Gemini 4 Argon Turns One Video Into a MuJoCo Sim, Apollo 2 Hits 7 Straight Shots — TechPreacher · 2026-10-26
• Alibaba's λ0 Trains Humanoid Robot with 500 Hours of Human Video — AIFlow_ML · 2026-10-26(4 related)
• Clean abstractions: human craftsmanship or RL giving us implicit world models? — akbirthko · 2026-10-26
• Anonymous Sleuth Shows Nature fMRI Foundation Model Paper Data Was Random, Seed 42 — bttyeo · 2026-10-26
• Learning RL From Scratch: Dev Publishes One-Page Basics Notes on neatrl.com — East-Muffin-6472 · 2026-10-26
• Token embeddings 'looked for' by value matrices but contribute little, analysis finds — RichmanRonald · 2026-10-26
• 'Neural optical flow': parameterizing classic CV circuits for faster network convergence — mike64_t · 2026-10-26
• Mira Murati's Claim That Abundant Compute Could Simulate Biology Sparks Debate — iScienceLuvr · 2026-10-26(5 related)
• New paper: training tasks act as attractors, clustering network weights by dataset — wschroll · 2026-10-26
• HIT Shenzhen unveils STILL: content-aware intra-layer hybrid attention to linearize LLMs — jiqizhixin · 2026-10-26
• Bambi quietly gains nonlinear model support, with a blog post showing how — twiecki · 2026-10-26