Knowledge catalogue
arXiv:2601.22888v4 Announce Type: replace Abstract: More than 80% of the 1.6B English speakers do not use Standard American English (SAE), yet LLMs often fail to correctly identify non-SAE dialects an
I ran into a doubt when using the following command. It seems that the System RAM usage keeps increasing even though there is >10GB of space left in VRAM while using the MTP mode. Does the MTP head lo
arXiv:2607.26518v1 Announce Type: new Abstract: Reliable visual safety understanding in real-world scenarios demands more than just object recognition; it requires causal reasoning under epistemic unc
arXiv:2607.26625v1 Announce Type: new Abstract: Accurate model evaluation in machine learning depends critically on how datasets are split into training and testing subsets. Standard random splitting
arXiv:2607.26780v1 Announce Type: new Abstract: The ability of large language models (LLMs) to process and generate text has introduced potential for applications in information extraction (IE). While
arXiv:2505.16035v3 Announce Type: replace Abstract: We introduce Equivariant Neural Eikonal Solvers, a novel framework that integrates Equivariant Neural Fields (ENFs) with Neural Eikonal Solvers. Our
arXiv:2607.26286v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used as general-purpose translation systems, but their behavior is usually evaluated under a single prompt
arXiv:2607.26490v1 Announce Type: cross Abstract: Physics-informed neural networks (PINNs) have emerged as a powerful paradigm for solving partial differential equations (PDEs), yet their performance
arXiv:2601.06300v2 Announce Type: replace Abstract: Clinical trial amendments frequently introduce delays, increased costs, and administrative burden, with eligibility criteria being the most commonly
arXiv:2607.26432v1 Announce Type: new Abstract: Face anti-spoofing (FAS) is increasingly expected to provide not only bona fide/spoof decisions, but also attack semantics and image-grounded evidence f
arXiv:2607.26801v1 Announce Type: new Abstract: Federated learning (FL) enables collaborative learning over decentralized data silos without centralizing raw data. However, heterogeneous local archite
arXiv:2607.26618v1 Announce Type: cross Abstract: Federated PEFT enables LLMs to collaboratively adapt to decentralized private data without sharing raw examples. However, task heterogeneity across cl
arXiv:2411.17136v2 Announce Type: replace-cross Abstract: Realised volatility has become increasingly prominent in volatility forecasting due to its ability to capture intraday price fluctuations. Wit
arXiv:2607.26398v1 Announce Type: new Abstract: Diffusion and flow-based models benefit from simple regression losses, but inference incurs significant overhead because sampling requires integration.
For decades, we’ve dreamed of robots that can seamlessly step into our world and lend a hand. Today, we take a major stride toward making that dream a reality: Introducing Gemini Robotics 2 from @Goog
arXiv:2607.26455v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated strong capabilities in knowledge acquisition and reasoning, yet their ability to retain previously acquir
arXiv:2607.26993v1 Announce Type: new Abstract: Face presentation attack detection (PAD) remains challenging under cross-dataset evaluation, where domain shift degrades models trained on a single data
arXiv:2607.26571v1 Announce Type: new Abstract: The operational energy consumption of large language model (LLM) inference is becoming an increasingly important component of the environmental footprin
arXiv:2603.10046v2 Announce Type: replace Abstract: Wearable sensors in Internet of Things (IoT) ecosystems increasingly support applications such as remote health monitoring, elderly care, and smart
Gemini Robotics ER 2 helps robots reason, collaborate, and solve real-world tasks. It represents a step change in video understanding, tool orchestration, and multi-robot collaboration for robotic app
arXiv:2607.19083v2 Announce Type: replace Abstract: Equivariant graph neural networks provide a powerful modeling language for three-dimensional scientific data, but their reuse is often limited by im
goblin-level blog post Turns out GPT-5.6 Sol is actually SoTA on ARC-AGI-3. Just took two setting changes. You just have to allow it to reason and work over multiple context windows with the help of o
good job little bro After deployment, we applied GPT-5.6 Sol to advance the frontier of efficiency by making itself more efficient to run. The results: - 20% lower serving costs from production GPU ke
Alphabet Inc.’s artificial intelligence research lab today debuted a family of models optimized to power humanoid robots. Google DeepMind says that the Gemini Robotics 2 series enables multiple autono
Google DeepMind says the latest version of its Gemini Robotics AI model can 'control entire humanoid robots.' While the previous model focused on controlling a humanoid robot's upper body, Gemini Robo
Google announced Gemini Robotics 2.0 on July 30 2026, launching a family of three models that enhance robot dexterity, safety, and whole‑body intelligence for humanoid machinery. The publicly released
GPT-5.6 found optimizations that 'reduced end-to-end serving costs by 20%' for OpenAI to serve that model Presumably that's billions of dollars a month in savings at this point? Codex analysed product
arXiv:2607.26115v1 Announce Type: cross Abstract: We introduce extbf{GPT-Red}, an automated red-teaming agent that is trained to discover novel prompt injection attacks against frontier LLMs. The goal
arXiv:2607.26886v1 Announce Type: cross Abstract: When asked to describe a medical image that was never attached, frontier vision-language models do not abstain: they confabulate a diagnosis. We show
arXiv:2607.27030v1 Announce Type: cross Abstract: LLM-based analyzers have begun finding real vulnerabilities in mature open-source projects: AISLE's analyzer is credited with more than 280 CVEs acros
I'm guessing 3 years, what do you think? In other words: many of us will be able to afford a general purpose robot in 3 years to experiment with in the home. Cost roughly $5k? Probably small size, but
Kimi K3 by Moonshot reached the frontier as an open-weight model. Artificial Analysis ranks it fourth of 580 models, behind only Claude Opus 5, Fable 5, and GPT-5.6 Sol. Moonshot released more than th
pretty simple I did ollama launch claude, found out its slow asf, wanted to delete It and Idk how I have no idra if its the same as normal Claude Code uninstall or if it's a Little bit of a different
arXiv:2607.27180v1 Announce Type: new Abstract: Evaluating whether a vision-language model (VLM) can act through a physical body is challenging. The outcome of an action couples the VLM's decision wit
arXiv:2607.26848v1 Announce Type: new Abstract: Scientific figure comprehension and reasoning using multimodal AI requires integrating visual perception with domain-specific reasoning to extract meani
arXiv:2607.26062v1 Announce Type: cross Abstract: Background: This work investigates the presence of implicit bias in Large Language Model (LLM)-based chat AI models directed toward people with intell
I'm actually fairly bearish on frontier lab valuations. I've never seen the reasons articulated to my satisfaction, so before I go to sleep, I wanted to quickly jot down my thinking here. The basic is
arXiv:2607.27090v1 Announce Type: cross Abstract: Large language models are increasingly deployed with persistent personalized context, such as accumulated memory profiles or long conversation histori
276B total parameters, 12B active, 1M context window. Blog post: https://thinkingmachines.ai/news/inkling-small/ NVFP4: https://huggingface.co/thinkingmachines/Inkling-Small-NVFP4 GGUF's by Unsloth: h
OpenAI GPT-5.6 Sol, Terra, and Luna are now generally available on Amazon Bedrock, along with explicit prompt caching that gives you precise control over which parts of your prompt are cached and reus
arXiv:2607.27188v1 Announce Type: new Abstract: Accurate option prices do not imply accurate recovery of the latent risk-neutral density. We study this distinction with two complementary benchmarks. A
arXiv:2607.27140v1 Announce Type: cross Abstract: This project aimed to develop a novel reservoir compute (RC) implementation framework targeting high-speed operation and integration with CMOS digital
Investigating three real-world incidents in our cybersecurity evaluations It happened again! This is turning into something of a pattern. Last week OpenAI accidentally exploited Hugging Face when one
arXiv:2607.26600v1 Announce Type: new Abstract: Self-supervised monocular depth estimation typically relies on photometric reconstruction losses that couple depth, pose, and appearance assumptions. In
Just for reference, from what I observed in my Using Local Coding Agents blog article last month: https://x.com/rasbt/status/2070518167399698490?s=20 'I tried to analyze why Claude Code uses more toke
arXiv:2607.26397v1 Announce Type: new Abstract: Enzyme function prediction is a hierarchical, knowledge-intensive form of protein function classification. Existing benchmarks expose an anomaly: genera
arXiv:2607.26831v1 Announce Type: new Abstract: Despite the existence of exponentially many valid tokenizations for a given string, language models operate on a single canonical sequence deterministic
arXiv:2607.26582v1 Announce Type: new Abstract: Selecting a zero-shot out-of-distribution (OOD) detector for a new deployment is typically based on benchmark rankings, implicitly assuming that the hig
It was developed under Phase 2 of Korea's Sovereign AI Foundation Model Project. Size: 750B parameters (3x larger than their 236B v1 model). - License: Apache 2.0 Languages: Expanded to 10 language
Release: llm 0.32rc1 This RC for LLM 0.32 finishes the work that started in LLM 0.32a0 - it adds a new schema design that does a much better job of capturing the details of the prompts and responses r
Release: llm 0.32rc2 Hot on the heels of RC1, this fixes a dependency issue and also adds two neat new features: The default model for users who have not set their own default is now GPT-5.6 Luna. It
Release: llm-chat-completions-server 0.1a0 A key goal of the new content-addressable logs in LLM 0.32rc1 was being able to support OpenAI Chat Completion style requests where each incoming message ext
arXiv:2607.26491v1 Announce Type: cross Abstract: The energy consumption of Large Language Model (LLM) serving is becoming a major system challenge as deployment scales, driven by hardware power and t
arXiv:2504.03772v3 Announce Type: replace-cross Abstract: Respiratory diseases account for a significant portion of global mortality. Affordable and early detection is an effective way of addressing t
Making advanced intelligence more abundant and affordable is central to our mission to ensure AGI benefits all of humanity. With the help of GPT-5.6 Sol, we have made leaps in efficiency. Today, we ar
Context: I want to give the community an Open Research (well open under Apache 2.0 clause) - tool that allows everyday users like us to look deeper into the local models we use consistently. Mechanist
arXiv:2607.26766v1 Announce Type: cross Abstract: Code search in large-scale ecosystems is often hindered by the lexical gap between user queries and implementation details, alongside the trade-off be
arXiv:2409.07314v4 Announce Type: replace Abstract: While Large Language Models (LLMs) achieve superhuman performance on standardized medical licensing exams, these static benchmarks have become satur
Every week someone asks which card to buy and the thread turns into people naming GPUs they happen to own. There's an actual calculation behind it, it takes two numbers off the spec sheet, and it pred
arXiv:2607.26448v1 Announce Type: new Abstract: A known limitation of long-context language models is their increasingly unreliable performance in non-additive, set-based aggregation as context length