AI Research

AI news coverage

293 articles across 98 editions

Articles

  1. Residual Connections and the Causal Shift: Uncovering a Structural Misalignment in Transformers -- 2026-04-08
  2. d318 is almost always suppressive in Qwen-2.5-3B emotional vectors, built an emotion vector steering pipeline -- 2026-04-08
  3. Training mRNA Language Models Across 25 Species for $165 -- 2026-04-08
  4. [Editorial] -- 2026-04-08
  5. Iran threatens $30bn Stargate AI hub in Abu Dhabi -- 2026-04-08
  6. mac-code: Claude Code Clone Running Free on Apple Silicon (35B at 30 tok/s) -- 2026-03-31
  7. autoresearch-mlx: Karpathy's Autonomous Research Loops on Apple Silicon -- 2026-03-31
  8. TurboQuant for Weights: Near-Optimal 4-bit LLM Quantization with Lossless 8-bit Residual -- 2026-03-31
  9. Copaw-9B: Alibaba's Official Qwen3.5 9B Agentic Finetune -- 2026-03-31
  10. [Editorial] Unsloth: #1 Trending Model for 3 Weeks -- 2026-03-31
  11. [Editorial] Vulnerability Research Is Cooked -- 2026-03-31
  12. [Editorial] Mad Bugs: Vim vs Emacs vs Claude -- 2026-03-31
  13. The Cognitive Dark Forest -- 2026-03-30
  14. $500K/year pharmacovigilance platform replicated in a weekend with Claude Code -- 2026-03-30
  15. Google Stitch is insane -- 2026-03-30
  16. [Editorial] Time Traveled from Frontier AI -- 2026-03-30
  17. [Editorial] Ambient Intelligence -- 2026-03-30
  18. [Editorial] -- 2026-03-25
  19. [Editorial] -- 2026-03-25
  20. Build a Domain-Specific Embedding Model in Under a Day (NVIDIA) -- 2026-03-24
  21. WMB-100K: Open Source Benchmark for AI Memory Systems at 100K Turns -- 2026-03-24
  22. Autoresearch on an Old Research Idea -- 2026-03-24
  23. Flash-KMeans: Fast and Memory-Efficient Exact K-Means -- 2026-03-20
  24. Autoresearch for SAT Solvers -- 2026-03-20
  25. Curriculum-DPO++: Direct Preference Optimization via Data and Model Curricula for Text-to-Image Generation -- 2026-03-20
  26. Code Concepts: A Large-Scale Synthetic Dataset Generated from Programming Concept Seeds -- 2026-03-19
  27. Provable Last-Iterate Convergence for Multi-Objective Safe LLM Alignment via Optimistic Primal-Dual -- 2026-03-19
  28. Neuro-symbolic experiment: training a neural net to extract its own IF–THEN fraud rules -- 2026-03-19
  29. [Editorial] AI Researchers Need to Know Statistics -- 2026-03-13
  30. [Editorial] Karpathy autoresearch -- 2026-03-10
  31. [Editorial] Doc-to-LoRA -- 2026-03-10
  32. We tested RLVR on top of fine-tuned small models across 12 datasets — here's exactly when it helps (and when it doesn't) -- 2026-03-02
  33. [Editorial] Weber Electrodynamics & Thermodynamic Memory -- 2026-03-02
  34. Minuspod: Automatically remove ads from podcasts locally -- 2026-03-02
  35. Squidcasa/midipipe: ALSA Sequencer to plain text and back -- 2026-03-02
  36. The Anxiety of Influence: Bloom Filters in Transformer Attention Heads -- 2026-02-20
  37. Higher effort settings reduce deep research accuracy for GPT-5 and Gemini Flash 3 -- 2026-02-20
  38. Consistency of Large Reasoning Models Under Multi-Turn Attacks -- 2026-02-16
  39. [Editorial] AI Testing and Quality Engineering -- 2026-02-16
  40. [Editorial] https://www.linkedin.com/posts/reuvencohen_i-believe-ai-is-one-of-the-most-powerful-activity-7427748896006737920-0U-U -- 2026-02-13
  41. [Editorial] https://steve-yegge.medium.com/the-ai-vampire-eda6e4f07163 -- 2026-02-11
  42. [Editorial] https://arxiv.org/abs/2602.05636 -- 2026-02-11
  43. [Editorial] https://www.linkedin.com/posts/reuvencohen_in-physics-time-is-how-we-order-events-and-activity-7427183754407964672-TFS_ -- 2026-02-11
  44. [Editorial] https://www.pantaos.com/en/post/a-friendly-walkthrough-of-how-large-language-models-are-trained -- 2026-02-11
  45. [Editorial] https://www.linkedin.com/posts/caleb-gross_agentic-llms-can-automate-vuln-detection-ugcPost-7427011167098777601-Xu0o -- 2026-02-11
  46. [Editorial] https://www.linkedin.com/posts/resilientcyber_probabilistic-tcb-activity-7427078167754113024-4XQN -- 2026-02-11
  47. [Editorial] https://www.linkedin.com/posts/yass-99637a105_this-last-month-ive-been-working-on-creating-activity-7427059163681325056-9q55 -- 2026-02-11
  48. [Editorial] https://arxiv.org/abs/2507.02735 -- 2026-02-11
  49. [Editorial] https://www.linkedin.com/posts/nikhil-vallishayee-81990615_ai-reflection-opus-activity-7425750279247044608-Nwne -- 2026-02-09
  50. [Editorial] https://www.linkedin.com/posts/robertgpt_saturday-ai-musings-in-the-1979-film-ugcPost-7426039060290490368-o3f2 -- 2026-02-09
  51. ChatGPT makes you smarter or dumber? -- 2026-02-09
  52. Semantic LLM Interpreter - only tested on a potato -- 2026-02-04
  53. Towards a science of scaling agent systems: When and why agent systems work -- 2026-02-04
  54. Teaching Models to Teach Themselves: Reasoning at the Edge of Learnability -- 2026-02-04
  55. Out-of-Distribution Generalization via Invariant Trajectories for Multimodal Large Language Model Editing -- 2026-02-04
  56. [Editorial] https://unhypedai.substack.com/p/the-knowledge-we-never-had-to-explain -- 2026-02-02
  57. [Editorial] https://www.linkedin.com/posts/reuvencohen_i-keep-coming-back-to-this-realization-and-activity-7415150024868892672-E4rE -- 2026-02-02
  58. [Editorial] https://arxiv.org/abs/2601.21279 -- 2026-02-02
  59. [Editorial] https://arxiv.org/html/2601.19897v1 -- 2026-02-02
  60. [Editorial] https://github.com/mitkox/SDFT -- 2026-02-02
  61. [Editorial] https://www.linkedin.com/posts/nwaisman_im-seeing-more-and-more-commercial-and-open-source-activity-7422623441268170754-NZhh -- 2026-01-29
  62. I made a Coding Eval, and ran it against 49 different coding agent/model combinations, including Kimi K2.5. -- 2026-01-29
  63. Do system prompts actually help? -- 2026-01-29
  64. facebookresearch/actionmesh -- 2026-01-27
  65. deepseek-ai/Engram -- 2026-01-27
  66. Multiplex Thinking: Reasoning via Token-wise Branch-and-Merge -- 2026-01-27
  67. [Editorial] https://www.linkedin.com/posts/charlesmartin14_%F0%9D%97%9C%F0%9D%98%83%F0%9D%97%B2-%F0%9D%97%BB%F0%9D%97%B2%F0%9D%98%83%F0%9D%97%B2%F0%9D%97%BF-%F0%9D%97%B3%F0%9D%97%B2%F0%9D%97%B9%F0%9D%98%81-%F0%9D%98%80%F0%9D%97%BC-%F0%9D%97%B3%F0%9D%97%AE-activity-7410533713505079297-qvtE -- 2026-01-23
  68. [Editorial] https://www.linkedin.com/posts/reuvencohen_yann-lecun-claiming-agi-again-and-this-time-activity-7420241622916939776-gbLX -- 2026-01-23
  69. MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching -- 2026-01-21
  70. [Editorial] https://github.com/7h30th3r0n3/Evil-M5Project -- 2026-01-20
  71. [Editorial] https://7h30th3r0n3.fr/the-vulnerability-that-killed-freewifi_secure -- 2026-01-20
  72. x86 prefixes and escape opcodes flowchart -- 2026-01-20
  73. [Editorial] https://forge-quality.dev/articles/anthropic-confirms-trenches-taught-us -- 2026-01-15
  74. Show HN: Chr2 – consensus for side effects (exactly-once is a lie) -- 2026-01-14
  75. MemRec: Collaborative Memory-Augmented Agentic Recommender System -- 2026-01-14
  76. [Editorial] https://cloudsecurityalliance.org/blog/2026/01/09/the-first-question-security-should-ask-on-ai-projects -- 2026-01-12
  77. [Editorial] https://github.com/leochlon/pythea/tree/main/strawberry -- 2026-01-12
  78. [Editorial] https://arxiv.org/abs/2509.11208 -- 2026-01-12
  79. Arbitrage: Efficient Reasoning via Advantage-Aware Speculation -- 2026-01-09
  80. [Editorial] https://www.linkedin.com/posts/vilhelm-von-ehrenheim_are-you-avoiding-the-dumb-zone-dex-dropped-activity-7414210431570993152-8AFP -- 2026-01-07
  81. [Editorial] https://www.linkedin.com/posts/cole-medin-727752184_2025-overpromised-on-ai-agents-2026-demands-activity-7414472389167841280-WDzs -- 2026-01-07
  82. [Editorial] https://www.linkedin.com/posts/ronitelman_the-missing-step-in-decision-intelligence-activity-7413638316899762177-Aifb -- 2026-01-07
  83. [Editorial] https://arxiv.org/html/2512.24601v1 -- 2026-01-06
  84. [Editorial] https://www.linkedin.com/posts/javier-cullas-644179109_ruvllm-llm-onlinelearning-activity-7414118850759262208-1Epx -- 2026-01-06
  85. [Editorial] https://github.com/Cornjebus/rlm-replication-study -- 2026-01-06
  86. [Editorial] https://www.linkedin.com/posts/reuvencohen_were-living-in-a-moment-that-would-have-activity-7414299558677233665-0__t -- 2026-01-06
  87. [Editorial] https://www.linkedin.com/posts/ownyourai_you-love-claude-code-i-love-claude-code-activity-7414258655698604032-HQL9 -- 2026-01-06
  88. [Editorial] https://www.linkedin.com/posts/reuvencohen_claude-flow-v3-is-coming-along-nicelyim-activity-7414048819975356416-dmg7 -- 2026-01-06
  89. I built a new fun art platform website where users can draw together with strangers to create a funny unexpected comic! - Antigravity helped build Sown! -- 2026-01-06
  90. infinigence/FUSCO -- 2026-01-02
  91. lightx2v/Qwen-Image-Edit-2511-Lightning -- 2026-01-02
  92. [Editorial] https://www.linkedin.com/posts/sergejepp_in-2001-a-kids-77-parameter-neural-net-activity-7406623412154044418-lgZj -- 2025-12-29
  93. [Editorial] https://docs.google.com/document/d/157QfISA6GhEc9cTly7DGecNqDXAbRJlsib-9JgXbRMA/edit?tab=t.0 -- 2025-12-29
  94. [Editorial] https://openreview.net/pdf?id=nbMeRvNb7A -- 2025-12-16
  95. Feedback Wanted - Vector Compression Engine (benchmarked v FAISS) -- 2025-12-16
  96. Why it so hard to abliterated kimi k2 thinking model? -- 2025-12-16
  97. MAA-AI/MaaMCP -- 2025-12-15
  98. Signature Forgery Detection: Improving Cross-Dataset Generalization -- 2025-12-15
  99. [Editorial] https://mindgard.ai/blog/google-antigravity-persistent-code-execution-vulnerability -- 2025-12-15
  100. [Editorial] https://www.linkedin.com/posts/jasonstanley2_trustworthyai-aisecurity-aisafety-activity-7405357983746109440-T6pE -- 2025-12-15
  101. It Only Takes a Handful of Samples To Poison Any Size LLM, Anthropic Finds -- 2025-12-15
  102. 🦜 VieNeu-TTS is officially COMPLETE! -- 2025-12-15
  103. HKUST-C4G/AnyTalker -- 2025-12-15
  104. inclusionAI/TwinFlow -- 2025-12-15
  105. eigen-ai-labs/eigen-banana-qwen-image-edit -- 2025-12-15
  106. SARLO-80: Worldwide Slant SAR Language Optic Dataset at 80 cm Resolution -- 2025-12-10
  107. 3D Gaussian and Diffusion-Based Gaze Redirection -- 2025-12-04
  108. PrimeIntellect/INTELLECT-3 -- 2025-12-04
  109. cerebras/MiniMax-M2-REAP-162B-A10B -- 2025-12-04
  110. Building Deep Research: How we Achieved State of the Art -- 2025-12-03
  111. [Editorial] https://www.linkedin.com/posts/ownyourai_nvidia-just-open-sourced-the-espresso-machine-activity-7401526786955812864-XUg2 -- 2025-12-02
  112. [Editorial] https://www.linkedin.com/posts/gadievron_introducing-raptor-an-autonomous-offensive-activity-7401533346238840832-6FxM -- 2025-12-02
  113. [Editorial] https://mavlevin.com/2025/11/30/cve-2022-35420-scada-lts-unauthenticated-account-takeover# -- 2025-12-02
  114. DataArcTech/DataArc-SynData-Toolkit -- 2025-11-28
  115. ORPO-Distill: Mixed-Policy Preference Optimization for Cross-Architecture LLM Distillation -- 2025-11-25
  116. Continuous batching from first principles -- 2025-11-25
  117. allenai/Olmo-3-32B-Think -- 2025-11-25
  118. tencent/HunyuanOCR -- 2025-11-25
  119. peteromallet/Qwen-Image-Edit-InScene -- 2025-11-25
  120. [Editorial] https://arxiv.org/html/2510.04871v1 -- 2025-11-24
  121. [Editorial] https://www.linkedin.com/posts/ingason_agenticai-erp-aiagents-activity-7396551539538141185-PxNU -- 2025-11-24
  122. facebook/sam3 -- 2025-11-24
  123. rl-research/DR-Tulu-8B -- 2025-11-24
  124. Fast and Fluent Diffusion Language Models via Convolutional Decoding and Rejective Fine-tuning -- 2025-11-24
  125. zai-org/Glyph -- 2025-11-21
  126. tlennon-ie/qwen-edit-skin -- 2025-11-21
  127. Mating Cycles: Engineering Connectors to Last -- 2025-11-21
  128. Commmunication-Efficient and Accurate Approach for Aggregation in Federated Low-Rank Adaptation -- 2025-11-21
  129. Gemini 2.5 Flash Image / Nano Banana Tutorial -- 2025-11-21
  130. [Editorial] Jailbreak -- 2025-11-21
  131. Anthropic - Disrupting the first reported AI-orchestrated cyber espionage campaign = "The threat actor—whom we assess with high confidence was a Chinese state-sponsored group" Link to report below -- 2025-11-21
  132. LuD1161/jsmon-go -- 2025-11-21
  133. Dissecting Flock Safety: The Cameras Tracking You Are a Security Nightmare [video] -- 2025-11-21
  134. Google cracked Apple's AirDrop and is adding it to Pixel phones -- 2025-11-21
  135. Last week in Multimodal AI - Local Edition -- 2025-11-12
  136. pnnbao97/VieNeu-TTS -- 2025-11-12
  137. FocalCodec-Stream: Streaming Low-Bitrate Speech Coding via Causal Distillation -- 2025-11-12
  138. [Editorial] https://www.suffsyed.com/futurememo/the-design-leaders-are-lying-to-you -- 2025-11-07
  139. KTransformers Open Source New Era: Local Fine-tuning of Kimi K2 and DeepSeek V3 -- 2025-11-04
  140. F2LLM Technical Report: Matching SOTA Embedding Performance with 6 Million Open-Source Data -- 2025-11-04
  141. Qwen/Qwen3-VL-235B-A22B-Thinking -- 2025-11-04
  142. [Editorial] AGI Defined. -- 2025-11-01
  143. VellumForge2 - A high performance, very configurable and really easy to use DPO dataset generation tool, create high quality datasets for completely free -- 2025-11-01
  144. PokeeAI/pokee_research_7b -- 2025-11-01
  145. [Editorial] https://pivot-to-ai.com/2025/10/15/ai-is-not-popular-and-ai-users-are-unpleasant-asshats/ -- 2025-10-30
  146. What's the best embedding model for document images ? -- 2025-10-26
  147. AlphaXiv,Compare the Deepseek-OCR and Mistral-OCR OCR models -- 2025-10-26
  148. Open-Bee/Bee-8B-RL -- 2025-10-26
  149. datalab-to/chandra -- 2025-10-26
  150. Unlock the power of images with AI Sheets -- 2025-10-26
  151. [Editorial] Leading AI Agent Swarms: The Agentic QE 1.2.0 Journey -- 2025-10-24
  152. lupantech/AgentFlow -- 2025-10-24
  153. jaguarliuu/xunlong -- 2025-10-24
  154. radicalnumerics/RND1-Base-0910 -- 2025-10-22
  155. Amadeus: Autoregressive Model with Bidirectional Attribute Modelling for Symbolic Music -- 2025-10-22
  156. Supercharge your OCR Pipelines with Open Models -- 2025-10-22
  157. DocReward: A Document Reward Model for Structuring and Stylizing -- 2025-10-22
  158. [Editorial] https://www.linkedin.com/pulse/building-17-quality-engineering-skills-how-i-turned-29-spiridonov-newhf -- 2025-10-19
  159. [Editorial] Brain vs body -- 2025-10-19
  160. [Editorial] Claude skills -- 2025-10-19
  161. [Editorial] Agentic Orchestration -- 2025-10-19
  162. MCPVerse: An Expansive, Real-World Benchmark for Agentic Tool Use -- 2025-10-19
  163. [Editorial] Claude Skills are awesome, maybe a bigger deal than MCP -- 2025-10-18
  164. [Editorial] Claude Skills -- 2025-10-18
  165. XiangShan Vector Floating-Point Unit Design -- 2025-10-07
  166. google/timesfm-2.5-200m-pytorch -- 2025-10-07
  167. svg-project/flash-kmeans -- 2025-10-07
  168. Dolphin — analyze-then-parse document image model (open-source, ByteDance) -- 2025-10-06
  169. Eclaire – Open-source, privacy-focused AI assistant for your data -- 2025-10-06
  170. KeyKnowledgeRAG (K^2RAG): An Enhanced RAG method for improved LLM question-answering capabilities -- 2025-10-06
  171. Granite 4 H Tiny Q8 in RTX 3090, It's a context king. -- 2025-10-06
  172. Paper2Agent: Stanford Reimagining Research Papers as Interactive AI Agents -- 2025-09-25
  173. GPT-OSS-120B Performance Benchmarks and Provider Trade-Offs -- 2025-09-20
  174. Why are there three different Codex variants? -- 2025-09-20
  175. [Editorial] which patterns truly survived compression -- 2025-09-16
  176. [Editorial] AI Kill Chain -- 2025-09-16
  177. TsinghuaC3I/Unify-Post-Training -- 2025-09-16
  178. The OSS code that powers Claude and the maintainer they didn't hire -- 2025-09-10
  179. Google's new AI mode is good, actually -- 2025-09-10
  180. Designing an Open Source Micro-Manipulator -- 2025-09-10
  181. iblameandrew/local-deepsearch-academic -- 2025-09-05
  182. From Libraries to Schools: Why Organizations Should Install Privacy Badger -- 2025-09-05
  183. Empirical Evaluation of Concept Drift in ML-Based Android Malware Detection -- 2025-09-05
  184. auth0/auth0-customer-detections -- 2025-09-05
  185. GPT OSS Fine-tuning QAT -- 2025-08-31
  186. Semantic Structure in Large Language Model Embeddings -- 2025-08-31
  187. facebook/dinov3-vit7b16-pretrain-lvd1689m -- 2025-08-31
  188. MizzenAI/HPSv3 -- 2025-08-31
  189. allenai/asta-paper-finder -- 2025-08-30
  190. [Editorial] 1984 -- 2025-08-30
  191. Doubling Your Data in Minutes: Ultra-fast Tabular Data Generation via LLM-Induced Dependency Graphs -- 2025-08-30
  192. Temporal Point-Supervised Signal Reconstruction: A Human-Annotation-Free Framework for Weak Moving Target Detection -- 2025-08-30
  193. AI Detection in 2025: What Actually Triggers Flags (and How to Write Like a Human) -- 2025-08-30
  194. [Editorial] Sense of Self and Time in Borderline Personality -- 2025-08-27
  195. Need advice on my approach in building a trending posts feature in my web app (React + Express.js) -- 2025-08-27
  196. [Editorial] Beyond LLM and SLM.. -- 2025-08-18
  197. Why it’s a mistake to ask chatbots about their mistakes | Ars Technica -- 2025-08-18
  198. Compliant Contacts: Hacking Door Locks with Pen Springs -- 2025-08-18
  199. Share Your Attention: Transformer Weight Sharing via Matrix-based Dictionary Learning -- 2025-08-18
  200. Feedback wanted on open-source LLM-as-a-Judge -- 2025-08-16
  201. Google's healthcare AI made up a body part -- 2025-08-16
  202. bosonai/higgs-audio-v2-generation-3B-base -- 2025-08-14
  203. Chain-GPT/Solidity-LLM -- 2025-08-14
  204. Bottom-up Domain-specific Superintelligence: A Reliable Knowledge Graph is What We Need -- 2025-08-14
  205. 🇵🇭 FilBench - Can LLMs Understand and Generate Filipino? -- 2025-08-14
  206. VisualTrap: A Stealthy Backdoor Attack on GUI Agents via Visual Grounding Manipulation -- 2025-08-10
  207. Wukong Framework for Not Safe For Work Detection in Text-to-Image systems -- 2025-08-10
  208. Automating Steering for Safe Multimodal Large Language Models -- 2025-08-10
  209. LoReUn: Data Itself Implicitly Provides Cues to Improve Machine Unlearning -- 2025-08-10
  210. Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face -- 2025-08-09
  211. [Editorial] https://unhypedai.substack.com/p/unhyped-ai-week-4-digest -- 2025-08-04
  212. 100+ AI Benchmarks list -- 2025-08-04
  213. google/langextract -- 2025-08-04
  214. Implemented Test-Time Diffusion Deep Researcher (TTD-DR) - Turn any local LLM into a powerful research agent with real web sources -- 2025-07-31
  215. Introducing Agent Data Shuttle (ADS): fully open-source -- 2025-07-31
  216. Introducing Trackio: A Lightweight Experiment Tracking Library from Hugging Face -- 2025-07-30
  217. [Editorial] Taking AI back from the sparkle ponies. -- 2025-07-28
  218. Toward Real-World Table Agents: Capabilities, Workflows, and Design Principles for LLM-based Table Intelligence -- 2025-07-26
  219. ICML 2025 Outstanding Paper Awards -- 2025-07-24
  220. Model to retrieve information from Knowledge. -- 2025-07-23
  221. merve/smol-vision -- 2025-07-23
  222. WhisPad (Note app, transcription, speaker diarization, AI style enhancements, mindmaps, chat with notes, etc) -- 2025-07-23
  223. new models from NVIDIA: OpenReasoning-Nemotron 32B/14B/7B/1.5B -- 2025-07-21
  224. OpenAI Places Second Behind Human Coder at AtCoder Progmming Event -- 2025-07-21
  225. HelpingAI/Dhanishtha-2.0-preview -- 2025-07-21
  226. Probing for Arithmetic Errors in Language Models -- 2025-07-21
  227. Laid off Candy Crush staff set to be replaced by the AI tools they helped build -- 2025-07-20
  228. A comprehensive study of LLM-based argument classification: from LLAMA through GPT-4o to Deepseek-R1 -- 2025-07-19
  229. Tencent-Hunyuan/Hunyuan-A13B -- 2025-07-14
  230. AI4Research: A Survey of Artificial Intelligence for Scientific Research -- 2025-07-13
  231. Owen777/Kontext-Style-Loras -- 2025-07-13
  232. Best Practices for Integrating Onyx (Danswer) with Open WebUI Pipelines -- 2025-07-13
  233. Just shipped first uvx compatible public pypi release for my automated Open WebUI Postgres migration tool -- 2025-07-13
  234. [P-6] Decoding FLUX.1 Kontext: Flow Matching for In-Context Image Generation and Editing in Latent Space -- 2025-07-13
  235. OLMo 2 - a family of fully-open language models -- 2025-07-12
  236. google/videoprism -- 2025-07-12
  237. AI Generated Text Detection Using Instruction Fine-tuned Large Language and Transformer-Based Models -- 2025-07-11
  238. Index academic papers and extract metadata with LLMs (Ollama Integrated) -- 2025-07-11
  239. HuggingFaceTB/SmolLM3-3B -- 2025-07-11
  240. Automated illustration of a Conan story using gemma3 + flux and other local models -- 2025-07-11
  241. krillinai/KlicStudio -- 2025-07-08
  242. Show HN: ParsePoint – AI OCR that pipes any invoice straight into Excel -- 2025-07-08
  243. kyutai/tts-voices -- 2025-07-08
  244. ByteDance/XVerse -- 2025-07-08
  245. Exploring Classical Piano Performance Generation with Expressive Music Variational AutoEncoder -- 2025-07-08
  246. 1000 African Voices: Advancing inclusive multi-speaker multi-accent speech synthesis -- 2025-07-06
  247. Hack Swaps Keys for Gang Signs, Everyone Gets In -- 2025-07-06
  248. Marker Gene Method : Identifying Stable Solutions in a Dynamic Environment -- 2025-07-06
  249. An optimizing compiler doesn't help much with long instruction dependencies -- 2025-07-04
  250. Linear Attention with Global Context: A Multipole Attention Mechanism for Vision and Physics -- 2025-07-04
  251. Transformers backend integration in SGLang -- 2025-07-04
  252. We build Curie: The Open-sourced AI Co-Scientist Making ML More Accessible for Your Research -- 2025-07-04
  253. Is there a local model that can solve this text decoding riddle? -- 2025-07-03
  254. Seven replies to the viral Apple reasoning paper and why they fall short -- 2025-07-03
  255. R1-0528 won't stop thinking -- 2025-07-03
  256. There are no new ideas in AI only new datasets -- 2025-07-02
  257. shyamsaktawat/OpenAlpha_Evolve -- 2025-06-28
  258. Top AI Models Compete in a Game of Diplomacy -- 2025-06-26
  259. The fastest way to detect a vowel in a string -- 2025-06-26
  260. MiniMaxAI/MiniMax-M1-40k -- 2025-06-18
  261. Qwen/Qwen3-Reranker-4B -- 2025-06-18
  262. 0.82 um 105 W diode-pumped thulium-doped all silica fiber laser -- 2025-06-17
  263. nanonets/Nanonets-OCR-s -- 2025-06-16
  264. Menlo/Jan-nano-gguf -- 2025-06-16
  265. 100% accurate Sudoku solving with deep learning algorithm -- 2025-06-15
  266. $0^{+}$ fully-charmed tetraquark states -- 2025-06-15
  267. MiniMax-AI/SynLogic -- 2025-06-15
  268. The Fractured Entangled Representation Hypothesis -- 2025-06-15
  269. BAAI/RoboBrain2.0-7B -- 2025-06-14
  270. facebook/vjepa2-vitl-fpc64-256 -- 2025-06-14
  271. showlab/D-AR -- 2025-06-14
  272. graphdeco-inria/on-the-fly-nvs -- 2025-06-14
  273. What's working for YC companies since the AI boom -- 2025-06-12
  274. 0-Hecke Modules, Domino Tableaux, and Type-$B$ Quasisymmetric Functions -- 2025-06-12
  275. Russia's Pravda Network: AI-Driven Disinformation on a Global Scale -- 2025-06-10
  276. meilisearch/meilisearch -- 2025-06-09
  277. 100,000 Podcasts: A Spoken English Document Corpus -- 2025-06-03
  278. nvidia/Nemotron-Research-Reasoning-Qwen-1.5B -- 2025-06-03
  279. Intelligent-Internet/II-Medical-8B -- 2025-06-03
  280. I Got llama-cpp-python Working with Full GPU Acceleration on RTX 5070 Ti (sm_120, CUDA 12.9) -- 2025-06-02
  281. 46pct Aider Polyglot in 16GB VRAM with Qwen3-14B -- 2025-06-02
  282. SAGA Update: Autonomous Novel Writing with Deep KG & Semantic Context - Now Even More Advanced! -- 2025-06-02
  283. Tiny agents from hugging face is great for llama.cpp mcp agents -- 2025-06-02
  284. Best settings for running Qwen3-30B-A3B with llama.cpp (16GB VRAM and 64GB RAM) -- 2025-06-02
  285. Ollama refuses to use GPU even on 1.5b parameter models -- 2025-06-02
  286. My pocket A.i is recognizing cars now -- 2025-06-02
  287. LLM performance variance depending on programming language -- 2025-06-02
  288. Suggestions to Improve My Ollama + Open WebUI Deployment on Coolify -- 2025-06-02
  289. What software do you use for self hosting LLM? -- 2025-06-02
  290. 0-1 phase transitions in sparse spiked matrix estimation -- 2025-06-01
  291. 0-Step Capturability, Motion Decomposition and Global Feedback Control of the 3D Variable Height-Inverted Pendulum -- 2025-06-01
  292. Model-Based Machine Learning (2023) -- 2025-05-28
  293. 0-MMS: Zero-Shot Multi-Motion Segmentation With A Monocular Event Camera -- 2025-05-28
  294. 0.8% Nyquist computational ghost imaging via non-experimental deep learning -- 2025-05-28