Search: “agents”

OpenAI is in the news again. This time, it’s due to a recent incident involving corporate espionage. According to a statement the AI lab released on 13th October, the company discovered a “sophisticat

arXiv:2610.14001v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) uses a self-teacher conditioned on privileged information to turn the sparse outcome signal of reinforcement learning

arXiv:2610.16967v1 Announce Type: new Abstract: Physical AI is commonly formulated around an explicitly specified task: given a goal or instruction, a system perceives, reasons, and acts. In many real

arXiv:2610.14635v1 Announce Type: cross Abstract: Large Vision-Language Models (LVLMs) have achieved remarkable progress across a wide range of multimodal tasks. However, object hallucination remains

arXiv:2610.16632v1 Announce Type: new Abstract: Memory-based long-video generation aims to combine user control with long-range visual consistency. We organize this process into three functional compo

arXiv:2610.14043v1 Announce Type: cross Abstract: Frontier language models reliably refuse to explain how to cause physical harm. We ask whether this refusal survives when the same models control a ro

arXiv:2610.17426v1 Announce Type: new Abstract: Clinical decision-making is a sequential process of information collection, clinical inference, and forecasting under partial observability, often witho

arXiv:2610.17867v1 Announce Type: new Abstract: Foundation models for tables and relational databases are increasingly used for predictive tasks across various scientific and industrial domains. Howev

arXiv:2610.16338v1 Announce Type: new Abstract: Recent years have witnessed rapid progress in joint audio--visual generation. However, audio--visual synchronization remains a challenge, as generated s

arXiv:2610.18256v1 Announce Type: new Abstract: On-policy self-distillation (OPSD) has emerged as a popular training paradigm for LLMs, providing dense, token-level supervision by aligning a model's o

arXiv:2610.15721v1 Announce Type: new Abstract: Cross-model KV cache sharing reduces prefill computation by allowing a receiver model to reuse prefix KV states generated by a related sender model. Exi

arXiv:2610.15961v1 Announce Type: cross Abstract: Emergent misalignment (EM) occurs when fine-tuning a language model to a narrow task makes it misaligned on unrelated ones. Because organizations now

arXiv:2610.15888v1 Announce Type: new Abstract: Reinforcement learning with verifiable rewards spends much of its rollout budget on states that yield no learning signal. We recast this as a question a

arXiv:2610.16735v1 Announce Type: new Abstract: Multimodal reinforcement learning with verifiable rewards commonly assigns one sequence advantage to an entire response. This outcome-level signal disti

arXiv:2610.17986v1 Announce Type: new Abstract: A common practice in instance retrieval is to grow the gallery size to improve a benchmark's discrimination capability. One prominent example is ILIAS,

NVIDIA RTX Spark is a new beginning for the PC — a reinvention combining the capabilities of a gaming PC, a creative studio and a personal AI supercomputer into a single superchip. With up to 128GB of

I'm a first year ML PhD at a T5 ML program in the US. I managed to get a first author paper accepted to NeurIPS Main Track last month and thought I'd start applying for PhD research internships since

The reality for most organizations is that data lives everywhere. As engineering teams expand and adopt specialized platforms for their workloads, enterprise data naturally disperses across multiple c

Grok @Bot rocks I've been using Grok @Bot as my daily driver for a few weeks now and: - it has replaced 100% of my search-like queries on chatgpt / claude - it has replaced 100% of my Hermes usage & a

So I wanted to try the horsey challenge myself on the latest engine i been testing which is a strata fork by sergqwer. https://github.com/sergqwer/strata-nvfp4. I seen a post earlier and seen i believ

Release: llm-gemini 0.35 I added support to llm-gemini for the new Gemini 4 Argon model, made available today via the Gemini API and for customers of their 100/month subscription plan. Here are the lo

I came across this blog post from OrcaRouter: https://www.orcarouter.ai/blog/qwen-3-8-next-vs-qwen-3-8 Not only is the blog post nonsensical in some parts, it's also completely without any value. It b

arXiv:2610.13669v1 Announce Type: new Abstract: Curriculum learning typically organizes training samples from easy to hard. In GRPO, medium-difficulty samples are attractive for online selection becau

arXiv:2610.13504v1 Announce Type: cross Abstract: Generative Recommenders increasingly use Reinforcement Learning (RL) to optimize outcomes that may appear hundreds or thousands of interactions after

arXiv:2610.13277v1 Announce Type: cross Abstract: Memory-augmented assistants retrieve evidence from stored conversations and documents to answer queries. Most embedding-based retrievers compare singl

tl;dr: Are there other models I should try? Is there something better than Kimi K3 for a code review? Is GLM-5.3 better at finding/patching security vulnerabilities? Are skills like https://github.com

Introducing RSI-Anything: Unlocking Recursive Self-Improvement with World Models 🚀 Can AI learn to improve itself by predicting the consequences of its actions? Built on JEPA-Anything, RSI-Anything us

🇫🇷 Le Chonk joins the sudo L7 leaderboard 🇫🇷 We just added @MistralAI's Mistral Large 4 to sudo L7, our benchmark for staff-level software engineering. Mistral Large 4 scores 13.3%, ahead of Muse Spar

arXiv:2610.13437v1 Announce Type: new Abstract: Anomaly detection, the identification of collision events that deviate from Standard Model expectations, is one of the most promising model-agnostic str

Microsoft Corp. today pulled back the curtains on Maia 300, its newest internally developed artificial intelligence accelerator. The chip is optimized for inference. Microsoft estimates that it can pr

Nvidia Corp. today announced new partnerships and contributions to the open-source community at the Open Compute Project Global Summit in San Jose, aimed at laying the foundation for the future of age

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:2610.13557v1 Announce Type: new Abstract: Anticipation of vessel trajectories is an essential task when navigating at sea. This applies to both human navigators and autonomous surface vessels. T

Recommended NVIDIA paper on memory-efficient post-training RL. A very interesting technique for scaling RL for LLMs. The main takeaway is that you can update all of a model's weights with RL and still

arXiv:2610.03994v2 Announce Type: replace-cross Abstract: VeriContest is a benchmark of 1007 competitive-programming problems in Rust, each with a Verus specification, a judge-accepted solution, and a

Inspired by DigUp for macOS, VectorDash aims to be a full Windows 11 search replacement, powered by EmbeddingGemma 2. Full indexing: search by meaning or exact words across photos, screenshots, audio,

We need a name for the kind of people that conflate 2022 pure LLMs that were in fact a tiny bit like stochastic parrots (not my phrase, and not one I ever endorsed) with 2026 systems that couple those

Financial institutions are adopting artificial intelligence faster than many compliance teams can establish the controls needed to oversee it. That gap is raising new questions about AI-powered compli

Summary of project status metrics Since StillDeadcode has released his new radiance inference engine, the writing is on the wall for the old vllm-radiance builds, people have moved on to newer and bet

I run local LLMs pretty much around the clock, but I also enjoy gaming on the same PC. Having models sitting in VRAM while gaming isn't exactly ideal, and constantly unloading and reloading them manua

There is a lot of discussion which quant to use. Especially a lot of post how much speed you gain with FP4, but not much about quality. So i tested some of the models that I use on my R9700. Models: Q

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

webAI released TwIL LM3 Pro on September 30. I haven't seen it posted here yet, so I went through the model card, and their comparison chart is attached. It's a 3.66B model built on IBM's Granite 4.2

For what it's worth. I'm a mechanical engineer by education and software engineer in practice over the past ~20 years. Playing around with local models has been a recent hobby. Today I decided to do a

I wanted to compare gemma 4 31b qat q4 and qwen3.8 27b iq4_nl, so I run SWEBench verfied on them. The original gemma 4 chat template doesn't work with preserve reasoning, so google released an update

Hi All: I have an Asus ESC 4000 G3 with 128 GB DDR4 RAM - I tried putting in my V620s but couldn’t put more than 2. Sadly, pivoted to T4s, these are 72 watt passive cards and I thought I could use the