Adaptive Policy Backbone via Shared Network
arXiv:2509.22310v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has achieved impressive results across domains, yet learning an optimal policy typically requires extensive intera
Knowledge catalogue
arXiv:2509.22310v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) has achieved impressive results across domains, yet learning an optimal policy typically requires extensive intera
AFAIK the most significant breakthrough since 2017 besides scaling old ideas was broadening from base models into larger systems that incorporate symbol/manipulating entities like harnesses, tools, an
arXiv:2607.29626v1 Announce Type: new Abstract: As LLMs evolve from code completion systems into autonomous scientific agents, evaluating their ability to conduct experiments has become increasingly i
arXiv:2603.20075v2 Announce Type: replace-cross Abstract: Compilers are critical to modern computing, yet fixing compiler bugs is difficult. While recent large language model (LLM) advancements enable
AI9Stars has released G9v3-39A5B an open weights language model designed to deliver even stronger reasoning capabilities than ai9stars/G9v3-3B with its 39B and 5 active experts. It is released under t
Alibaba Group Holding Ltd. today debuted a new addition to its Qwen series of open-source large language models. Qwen3.8-Max is the Chinese e-commerce giant’s most capable LLM to date. It features 2.4
All frontier AI models (including GPT-5.6 Sol, Fable 5, and Kimi K3) consistently fail to implement solvers for basic nonlinear PDEs correctly, often introducing significant errors in numerical stabil
arXiv:2607.29549v1 Announce Type: new Abstract: Large language models have demonstrated strong mathematical problem-solving capabilities, yet reliably verifying their candidate answers remains challen
An internal version of our next major model produced 10 new results on long-standing open problems in mathematics and theoretical computer science, using roughly $2,000 worth of tokens at GPT-5.6 Sol
arXiv:2607.29456v1 Announce Type: cross Abstract: Double Machine Learning (DML) is a popular approach for treatment effect estimation in various settings, which allows a wide range of flexible machine
Qwen3.8-Max from Alibaba’s Qwen team achieved second place in the Vision Arena benchmark, scoring 1,305 points. It trails only Claude Fable 5 (High), which leads by a slim 13‑point margin. The post un
arXiv:2607.29539v1 Announce Type: cross Abstract: Standard AI-text detection benchmarks compare human-written text against text generated directly by large language models (LLMs). While prior work has
arXiv:2607.28661v1 Announce Type: new Abstract: Do Large Language Models (LLMs) possess genuine structural reasoning, or merely rely on surface-level pattern matching? The financial domain, demanding
Eduardo Baptista / Reuters: Artificial Analysis: DeepSeek's V4-Flash costs 0.14/1M input and 0.28/1M output tokens, or 0.03 per test, far below Kimi K3's 0.86 and GPT-5.6 Sol's $1.86 — A version of Ch
🚨ASI/AGI is imminent fans don’t realize that they ALREADY lost the argument around Astra. My argument (spelled out in detail in my Substack today) was that Astra was unlikely to be the dramatic leap f
Qwen from Alibaba has released the Qwen 3.8‑Max model on the Venice platform, enabling users to ask questions anonymously. The announcement encourages users to try the new functionality immediately. T
arXiv:2607.29293v1 Announce Type: new Abstract: Accurate fault location is critical for distribution network reliability. However, increasing distributed energy resource (DER) penetration complicates
arXiv:2607.29055v1 Announce Type: cross Abstract: Multi-agent systems (MAS) are increasingly deployed to solve complex tasks. In case of incorrect or unsatisfactory outputs, users have to manually loc
metal: implement DSv4 Lightning Indexer (#25893) metal: implement F16 Lightning Indexer Implement GGML_OP_LIGHTNING_INDEXER for 128-dimensional, 64-head inputs with F32 queries and weights plus F16 ke
llama : MTP support for DeepSeek V3.2 (#26457) llama : MTP support for DeepSeek V3.2 model : no need to include MTP layers during DeepSeek V3.2 model type discovery Co-authored-by: Stanisław Szymczyk
model: MTP support for Qwen3-Next (#25589) mtp for qwen3nex fix for python type-check Fix to compute num_mtp from directly mtp layer define opt_num_mtp_layers in _QwenMtpMixin and fix some comments Fi
server: add notice for upcoming default port change 8080 --> 9931 (#26508) server: add notice for upcoming default port change 8080 --> 9931 add link to PR correct to 9931 Website: https://llama.app m
CUDA: Fix data-races when reusing SMEM in block_reduce (#26385) CUDA: Fix data-races when reusing block_reduce block_reduce currently doesn't resync after reading from SMEM, causing potential data-rac
CUDA: Add backend sampler for penalties sampler (#25262) sampling: enhance penalty handling in common_sampler_init Set default value for penalty_last_n based on model context if not specified. Ensure
llama : allocate indexer cache only in 'full' indexer layers (#26474) Co-authored-by: Stanisław Szymczyk sszymczy@gmail.com Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Appl
model: M3: Move MSA into a new memory implementation (#26338) Move MSA logic from llama-kv-cache into llama-kv-cache-msa cont : minor cont : ws fix Co-authored-by: Georgi Gerganov ggerganov@gmail.com
graph : fix unused input tensors in minimax m3 graph (#26519) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64)
opencl: route large q6_K lm_head to the flat GEMV (#26427) add a direct size condition for large weights; the original dimension condition is insufficient -- q6_K lm_head for gemma-4 E2B has [1536, 26
arXiv:2607.29064v1 Announce Type: cross Abstract: Police crash narratives contain information that may supplement structured crash databases, but manual review is labor-intensive and it remains unclea
arXiv:2607.28801v1 Announce Type: cross Abstract: Benchmark datasets are central to evaluating Large Language Models (LLMs), yet they are typically conceived as monolithic tasks, obscuring substantial
arXiv:2607.28840v1 Announce Type: new Abstract: Large language models are increasingly deployed in financial applications that combine retrieval, proprietary data, tool use, orchestration logic, monit
arXiv:2607.29640v1 Announce Type: new Abstract: Flexible manufacturing requires rapid deployment of solutions and minimal setup time to remain competitive. An essential attribute is the ability to con
Does anyone have an idea, when OpenAI will fix ChatGPT's glitched images? Since the 2.0 image generator was released, there is ugly glitches when you use generated image as a reference or just change
arXiv:2607.29302v1 Announce Type: cross Abstract: Reliable robot learning requires a world simulator that can predict action consequences before execution on physical hardware, including risky and fai
arXiv:2607.28991v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in multimodal understanding and generation. However, when textual inp
arXiv:2607.28631v1 Announce Type: new Abstract: AI Scientist systems capable of autonomous research have the potential to significantly accelerate scientific discovery. However, evaluating and compari
arXiv:2603.03322v2 Announce Type: replace-cross Abstract: Recent advancements in Large Language Model (LLM) agents have demonstrated remarkable potential in automatic knowledge discovery. However, rig
arXiv:2607.28634v1 Announce Type: new Abstract: The estimation of item difficulty plays a key role in both formative assessment and large-scale high-stakes summative assessments. This study explores h
Networking and security company Cato Networks Ltd. today introduced Cato Agentic Threat Prevention, a capability that uses autonomous agents to predict the route an attacker is likely to take through
arXiv:2607.29253v1 Announce Type: cross Abstract: Medical image quality plays a critical role in diagnostic accuracy, especially in X-ray-based imaging modalities such as cone-beam computed tomography
Chinese tech giant Alibaba released what it says is its largest and 'most capable AI model to date,' claiming performance rivaling the best systems from US frontier labs Anthropic and OpenAI, as well
arXiv:2602.11885v2 Announce Type: replace Abstract: Diffusion-based policies generalize poorly in semantic manipulation, a key obstacle to real-world deployment, because text-only instructions cannot
arXiv:2607.29172v1 Announce Type: cross Abstract: While robot foundation models are growing increasingly capable, the strongest models are typically trained on proprietary data and remain closed-sourc
arXiv:2607.19338v2 Announce Type: replace Abstract: Coding agents increasingly operate in executable environments where a failed attempt produces actionable feedback rather than merely an incorrect an
arXiv:2502.19135v2 Announce Type: replace Abstract: We present PLANTOR, a framework for generating and executing multi-robot task plans from natural-language task descriptions through LLM-assisted kno
arXiv:2405.07708v3 Announce Type: replace Abstract: Decentralized learning (DL) enables participants to collaboratively train models without a central server, yet it faces significant scalability chal
Businesses want to quickly and safely deploy AI agents to drive revenue, mitigate risk, and optimize capital, all without disrupting mission-critical ERP systems. And to power AI agents, you need more
arXiv:2607.28649v1 Announce Type: cross Abstract: COSI-Lab presents a multimodal, multi-sensor dataset of an interdisciplinary scientific workshop containing 32 academics at an international conferenc
Artificial intelligence has become a target for attackers rather than only a tool they use, according to CrowdStrike Holdings Inc.’s “2026 Threat Hunting Report,” released today. The annual report dra
arXiv:2607.29120v1 Announce Type: new Abstract: Relational Prior-Data Fitted Networks (PFNs) such as RDB-PFN approximate Bayesian inference over multi-table relational databases by pretraining on mill
arXiv:2607.29011v1 Announce Type: new Abstract: Traversing crests, ledges, and ditches at high speed often launches vehicles into the air, and a mishandled landing presents a substantial crash hazard.
arXiv:2607.29078v1 Announce Type: new Abstract: On-policy distillation (OPD) trains student models on their own rollouts to reduce exposure bias. However, in multi-turn agent scenarios, early student
I've been out of these forums for awhile but I figured I would provide a formal update on how this has been going now that it has some operation time under its belt, just to put the information out th
arXiv:2607.29250v1 Announce Type: new Abstract: Small language models (SLMs) are attractive for agentic deployment due to low latency, reduced cost, and on-device privacy, yet they struggle with tool-
Originally, I was only getting around 140pp/s and about 21tg/s, but the config with -b 8192 -ub 8192 --cpu-moe is vastly superior, let's say 700pp/s and 18tg/s in the most relevant range. Test System:
Ran DeepSeek V4-Flash-0731 — the full official checkpoint, not a re-quant — on commodity used hardware. Sharing because I couldn't find anyone else publishing Ampere results for this engine. Why bothe
arXiv:2605.05895v2 Announce Type: replace-cross Abstract: Modern AI-generated videos are photorealistic at the single-frame level, leaving inter-frame dynamics as the main remaining axis for detection
arXiv:2607.29188v1 Announce Type: new Abstract: Migrants traversing geographically distinct routes such as the Trans-Saharan and Balkan corridors often recount strikingly parallel lived experiences: p
My comment on Devtools must be open source (exe.dev) — Hacker News.One of the arguments for open source software for end-users has always been the freedom to examine and modify how that software works
arXiv:2607.28936v1 Announce Type: cross Abstract: Facial biometric identification relies on the distinctiveness of user attributes within a high-dimensional embedding space. However, the decision boun