All entries

We turned @OpenAI's math problems into open-source RL environments on @huggingface! Early and rough (the verifier only accepts the exact original formalization, so an equivalent proof can still score

I stumbled across this as I was currently having glm5.3 flash run only around 10tok/s basically unusable. With Maya i am running 30 tok/s now. GLM5.3 feels even with this low quant like a much more en

CBS News: Q&A with Palantir CTO Shyam Sankar on the Iran school strike and AI targeting, the DOD dropping Anthropic, AI liability, effective altruism, and more — The following is the full transcript o

No more excuses for GPU-poor folks not to start LLMing! Full 27B-class reasoning in ternary transformer weights, for llama.cpp (CUDA, Metal, CPU) ~9.3x smaller than FP16 (ideal) | 98.2% of FP16 intell

Achint Srivastava / Command Line: Microsoft unveils Microsoft-Decision-1, a fast decision-scoring model trained on Qwen3.5-9B, and says it will soon rebase it on MAI, OpenAI, and other models — Decisi

Dusting off this tweet from April because this gap in shared understanding of LLM capability is *widening*. It's now less 'two groups of people speaking past each other' and more a sharp funnel. - Nap

Tony Diver / Telegraph: Sources: the US restores the UK AISI's access to the latest US models for safety testing, after ordering OpenAI and Anthropic to stop sharing models last month — US had blocked

I wanted to track grocery spending per item without sending my receipts to anyone, so I built an Android app around a small vision model that reads a photo of a receipt into JSON: store, date, total,

I recently started using local LLM for mostly coding tasks for my personal projects. I also have found local models responding much better for topics such as health, fitness, ergonomics etc. compared

Ive been using OpenWebUI's inbuilt web search and I can't put my finger on it, but it's not quite as polished, reliable, seamless as using Claude or Gemini. And its often slow beyond a limit that make

Tony Diver / Telegraph: Sources: the US restores the UK AISI's access to the latest US models for safety testing, after ordering OpenAI and Anthropic to stop sharing models last month — US had blocked

arXiv:2610.12802v1 Announce Type: new Abstract: A conversational speech model has to decide, at every pause, whether to speak. Existing evaluations test boundary detection, policy adherence, or aggreg

arXiv:2610.12954v1 Announce Type: new Abstract: This paper introduces MathVis, a benchmark designed to evaluate LLMs' ability to visualize frontier mathematical problems and perform diagram-assisted r

arXiv:2610.13623v1 Announce Type: cross Abstract: Professional agents increasingly work through command-line interfaces and multiple tools over shared workspaces containing files, messages, and busine

Madhumita Murgia / Financial Times: An interview with ex-DeepMind scientist David Silver on his startup Ineffable, building an AI “super learner” using RL as an alternative path to LLMs, and more — Th

arXiv:2610.13184v1 Announce Type: new Abstract: While reinforcement learning with verifiable reward (RLVR) enhances reasoning in large language models, its efficacy in long-horizon multimodal tasks re

arXiv:2610.13257v1 Announce Type: cross Abstract: Cross-tokenizer on-policy distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text alignme

arXiv:2610.12711v1 Announce Type: new Abstract: Federated Large Language Models (FedLLMs) are promising to deliver privacy-preserving, collaborative intelligence. The decentralized training process is

vulkan: use ternary expressions to avoid switch lowering for CM2 quant block size (#30164) vulkan: specialize quant block size for CM2 matmul vulkan: use ternary expressions to avoid switch lowering f

ggml: Change default visibility of symbols to hidden (#30014) See discussion in #29997. This prevents a handful of internal symbols leaking via GGML_API. Website: https://llama.app Attestations: https

vulkan: fix buffer logging on 32-bit platforms after source split (#30326) Move the vk::Buffer stream operator to the shared header so it is visible to ggml-vulkan-debug.cpp. Website: https://llama.ap

hexagon: add IM2COL_3D (#30305) hexagon: add IM2COL_3D support Assisted-by: OpenCode hexagon: add DMA paths for IM2COL_3D Assisted-by: OpenCode hexagon: avoid scalar fp16 conversions in IM2COL Assiste

arXiv:2610.13078v1 Announce Type: new Abstract: Safety-aligned large language models (LLMs) remain vulnerable to jailbreaks and can over-refuse benign requests. Understanding these failures requires d

arXiv:2610.13303v1 Announce Type: cross Abstract: LLM judges are increasingly deployed as panels, and disagreement among panel members is often read as a symptom of an unclear rubric. We test a label-

OpenAI released 719 mathematics manuscripts on October 6, 2026 that were generated by an internal frontier model (not publicly available), covering 372 topic families—including a solution to the Navie

arXiv:2610.11160v1 Announce Type: new Abstract: Lifelong editing of LLMs requires storing thousands of edits after acquisition. A widely used family of approaches attaches one LoRA adapter per edit, w

I’m in Seoul building Mistral’s founding Korea team. Looking for kind, ambitious researchers and engineers to build and customise LLMs for real problems, from data and evals to RL and training at scal

It seems Dario's 'too powerful for you users' strategy is paying off: we have two open models at the top of the leaderboard, surpassing every single model from Anthropic. Open source prevails. Even Mi

Mistral OCR is on OpenDocRouter! For its price, it is decent over tables and reading order. It's also blazing fast at p50 1.8s per page We're constantly bringing in new models since OpenDocRouter laun

It's been 4 years since c.ai first hallucination model, and yet, we're nowhere good enough at LLMs in terms of spontaneity/interesting hallucination features. Fortunately, last year brought new archit

EXL3-QLoRA I've built this over the last few months and I think it's stable enough to share now. A fork of ExLlamaV3, this is a native ExLlamaV3 training implementation with plain PyTorch, without tra

arXiv:2610.13257v1 Announce Type: cross Abstract: Cross-tokenizer on-policy distillation (OPD) requires aligning teacher and student sequences before their scores can be compared. Decoded-text alignme

Aisha Malik / TechCrunch: AI hardware startup Natura unveils Interface, a 99 smart ring that connects to AI agents and apps, including Claude, ChatGPT, Muse, Grok Bot, and Instinct — Meet Interface, a

arXiv:2610.10622v1 Announce Type: cross Abstract: Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable. Existing judges tak

For those of you who have been wanting to utilize your dual Spark cluster for image/video gen with ComfyUI - today is your day. I started this personal project back in April of this year, and it’s at

arXiv:2610.12802v1 Announce Type: new Abstract: A conversational speech model has to decide, at every pause, whether to speak. Existing evaluations test boundary detection, policy adherence, or aggreg

arXiv:2610.12493v1 Announce Type: new Abstract: Explainable Artificial Intelligence (XAI) tools have often been presented as methods to increase trust in machine learning models by making aspects of t

🚨 Elon Musk agrees with 'some of the things Anthropic has said' and warns against 'torturing superintelligence' after reading Grok's internal reasoning traces during reinforcement learning “It feels l

arXiv:2610.12915v1 Announce Type: new Abstract: Minimax optimization is fundamental to adversarial learning yet suffers from severe stability challenges, often manifesting as persistent limit cycles o

arXiv:2610.12703v1 Announce Type: cross Abstract: High-risk applications of deep learning require precise characterization of model decision-making. We conduct a systematic explainability evaluation a

arXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still

arXiv:2610.13563v1 Announce Type: cross Abstract: Repository-level issue-resolution benchmarks such as SWE-bench evaluate submitted patches primarily based on whether they pass the correctness tests,

arXiv:2610.12659v1 Announce Type: new Abstract: Data-centric scaling of RLVR has focused on collecting or generating verifiable training problems. However, corpus size alone does not determine whether

arXiv:2610.13128v1 Announce Type: new Abstract: Question answering over large heterogeneous document collections requires first finding the right passages and then reading them, yet current retrieval-

arXiv:2606.15419v2 Announce Type: replace-cross Abstract: Objective: To enhance the accuracy, interpretability, and robustness of large language models (LLMs) in medical question answering (MedQA). Me

arXiv:2610.12610v1 Announce Type: cross Abstract: Ethnic and cultural identities rarely align with political borders, a tension made sharper by migration and long-standing cross-border ties. Communiti

arXiv:2610.13948v1 Announce Type: new Abstract: Language models increasingly support or automate information retrieval from document collections too large to index. This task is difficult when it requ

arXiv:2610.13708v1 Announce Type: new Abstract: Long-context serving runs out of KV memory before the hardware reaches its useful throughput. HiSparse stores history in host memory and fetches only th

Alright, I learend a few valuable lessons since I posted about a week ago, and I've made more strides with the DDR4x Ascend 96GB 310P cards I purchased, so here we go, meet the new friendly and less v

I stumbled across this as I was currently having glm5.3 flash run only around 10tok/s basically unusable. With Maya i am running 30 tok/s now. GLM5.3 feels even with this low quant like a much more en

Nvidia Corp. is in early talks to acquire open-weight model developer Reflection AI Inc. or invest more in the startup, according to the Financial Times. People familiar with the matter told the paper

DISCLAIMER: the post and the model card was made with the assist of AI. Hiya, I’m releasing Recursive BitNet N-Gram 102M, a small experiment combining ternary weights, shared transformer layers, and h

It's been 4 years since c.ai first hallucination model, and yet, we're nowhere good enough at LLMs in terms of spontaneity/interesting hallucination features. Fortunately, last year brought new archit

arXiv:2610.13325v1 Announce Type: cross Abstract: Agentic workloads resend long contexts that barely change between calls. Prefix caching now skips most of their prefill, yet every request must still

arXiv:2610.13041v1 Announce Type: new Abstract: Recurrent-depth language models improve inference-time reasoning by repeatedly applying a shared network to refine internal representations, but the add

Write-up, serve command and raw data: https://github.com/lukolszewski/vllm This shows vLLM fixes and setup that let you put PLE on SSD and save 108GB of system RAM, use int8 kv and squeeze more users