Knowledge catalogue
arXiv:2607.09080v2 Announce Type: replace Abstract: Although Video Large Language Models (Video LLMs) have shown strong performance in video understanding, their efficiency is still limited by the lar
arXiv:2512.24592v3 Announce Type: replace Abstract: Systematic failures of vision models on semantically coherent subsets, known as error slices, reveal limitations in robustness and evaluation. Exist
Great paper on self-improving agent harnesses. (bookmark it) If you maintain a production agent harness, finding every file behind one behavior is often harder than writing the edit. Harness Handbook
arXiv:2607.19355v1 Announce Type: new Abstract: LLMs are increasingly used with external knowledge sources like the internet. Do they weigh information appropriately -- updating more for reliable sour
arXiv:2602.22649v2 Announce Type: replace Abstract: Interactive Medical-SAM2 GUI is an open-source desktop application for semi-automatic annotation of 2D and 3D medical images. Built on the Napari mu
arXiv:2607.20056v1 Announce Type: cross Abstract: Aspect-based sentiment analysis (ABSA) in Arabic must recover both explicitly stated aspects and implicit aspects that are never named in the text. Im
arXiv:2607.20410v1 Announce Type: new Abstract: Value alignment of Large Language Models (LLMs) has been shown to be culturally biased toward Western norms. This results in the mishandling of local va
arXiv:2512.05462v2 Announce Type: replace-cross Abstract: Pharmaceutical drug discovery demands machine learning (ML) infrastructure that goes beyond general-purpose Machine Learning Operations (MLOps
arXiv:2607.20241v1 Announce Type: cross Abstract: Culturally loaded translation poses unique challenges for machine translation (MT), as meanings are deeply embedded in socio-cultural contexts beyond
arXiv:2607.19856v1 Announce Type: cross Abstract: FinMMEval 2026 Task 1 evaluates multilingual financial multiple-choice question answering in English, Chinese, Arabic, and Hindi. The task tests wheth
arXiv:2607.20145v1 Announce Type: cross Abstract: Full-parameter post-training of trillion-parameter-scale MoE models introduces substantial system-level challenges for large-scale distributed trainin
arXiv:2602.13935v2 Announce Type: replace Abstract: While LLMs have seen substantial improvement in reasoning capabilities, they also sometimes overthink, generating unnecessary reasoning steps, parti
arXiv:2607.20208v1 Announce Type: new Abstract: Surprisal Theory is often characterized as a computational-level explanation per (Marr, 1982). We argue in this work that, even though a computational l
Welcome to The Blueprint, a new feature where we highlight how Google Cloud customers are tackling unique and common challenges across industries using the latest AI and cloud technologies. We hope to
TL;DR: Everyone says QLoRA past ~13B is dead on a 24GB card. I got the full 32B FLUX.2 dev transformer QLoRA-training resident on the GPU on a 7900 XTX under native ROCm on Windows (no ZLUDA, no CUDA
Wish Dario had taken this bet. 🎺 I am hereby publicly offering to bet @darioamodei $1,000,000 that AI in 2027 will NOT be “smarter than Nobel Prize winners across most fields in science and engineerin
Guys, this is my current opencode.jsonc ``` { '$schema': 'https://opencode.ai/config.json', // Start in plan mode 'default_agent': 'plan', // Use OpenRouter as the provider for GLM 5.2 'model': 'openr
just watched @yoheinakajima's Active Graph talk at AI Engineer. not a code call graph but the agent run itself is the graph: goals, tasks, evidence, decisions, all projected from an append-only event
Fara1.5-27B is a multimodal computer use agent (CUA) for web browsers, from Microsoft Research AI Frontiers. It observes the browser through screenshots and acts on the user's behalf by emitting struc
New research from Meta. (bookmark it) Most factuality work checks whether the claims in an answer are correct. GAMUT goes after the harder question of whether the answer covers everything it should. I
Domesticated, not feral: Why evolvable AI is not yet a Darwinian threat Writing in PNAS (Proceedings of the National Academy of Sciences), three heavyweights in AI and evolutionary biology criticized
Not because Andrej is saying it but I think voice is goated. And you can mix it with other modalities for even richer prompting. I recorded a session a few weeks back to demo the power of multimodal p
As adversarial AI threats accelerate attacks on code, security teams must counter them with machine-speed defenses that can automate code remediation and fight AI with AI. CodeMender is our managed co
Huge launch from @tryramp. Different steps in an agent workflow can use different models. This can help reduce costs significantly without sacrificing performance. Model routing will become a core par
Who’s Afraid of Chinese Models? Interesting proposal from Ben Thompson that both addresses the hypocrisy of labs outlawing distillation against their models despite training on unlicensed data, and co
arXiv:2607.13899v1 Announce Type: new Abstract: We propose the AIMO Interpretability Challenge, a competition on distinguishing robust from spurious reasoning in frontier mathematical language models
arXiv:2607.14049v1 Announce Type: new Abstract: The emergence of Chain-of-Thought (CoT) reasoning has significantly enhanced the ability of large language models (LLMs) to tackle complex, multi-step t
arXiv:2607.13416v1 Announce Type: new Abstract: Automating analog circuit topology design is essential to reduce the extensive manual effort required to meet increasingly diverse and customized applic
arXiv:2607.13921v1 Announce Type: cross Abstract: Languages with rich static semantics, such as Rust, provide stronger guarantees for AI-generated code, but their strictness makes generation more diff
arXiv:2510.10002v3 Announce Type: replace Abstract: As large language models (LLMs) are increasingly deployed in sensitive everyday contexts -- offering personal advice, mental health support, and mor
arXiv:2607.13245v1 Announce Type: new Abstract: While 3D Scene Graphs (3DSGs) provide crucial structured representations for embodied agents, conventional Ahead-of-Time, build-everything-then-filter p
arXiv:2607.13501v1 Announce Type: new Abstract: Reinforcement learning for multi-turn search reasoning typically relies on terminal outcome rewards, which cannot distinguish useful, redundant, and har
arXiv:2607.14047v1 Announce Type: new Abstract: Autonomous data collection governs the volume and quality of real-world trajectories for manipulation policy learning. Existing pipelines reduce human e
arXiv:2607.13104v1 Announce Type: new Abstract: Self-improving autonomous agents are moving from research prototypes to deployed systems. The primary goal is controllable evolution, or adaptation, fro
arXiv:2607.13111v1 Announce Type: cross Abstract: Distinguishing semantic-preserving commits from changing ones remains an open challenge in software repository mining. While existing approaches detec
arXiv:2607.13099v1 Announce Type: cross Abstract: Large language models (LLMs) have achieved remarkable success but raise growing concerns about content provenance and misuse, motivating the need for
arXiv:2607.11918v1 Announce Type: cross Abstract: Dual submissions, in which identical or substantially similar papers are simultaneously submitted to one or more archival venues, without cross-citati
arXiv:2607.10383v2 Announce Type: replace-cross Abstract: Visual Language Navigation foundation models aim to unify deep reasoning for grounded spatial decisions with broad versatility for diverse emb
AI agents are already being used to improve the capabilities of our next-generation models. We believe with GPT-Red that we have started to unlock a similar flywheel for safety, where today's models c
arXiv:2607.12181v1 Announce Type: new Abstract: Robot gaze is a major component of human-robot dialogue coordination. Most studies of gaze in human-robot dialogue focus on face-to-face social conversa
DeepseekV4: reduce graph splits (#25702) macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework Linux: Ubuntu x64 (CPU) Ubuntu
arXiv:2607.11940v1 Announce Type: cross Abstract: As the scale of large pre-trained models continues to grow, fine-tuning them under limited memory budgets has become increasingly challenging. Low-Ran
arXiv:2607.13007v1 Announce Type: new Abstract: Simulation-based algorithms are especially suited for high-uncertainty environments such as adversarial board games with significant elements of randomn
arXiv:2607.12928v1 Announce Type: new Abstract: We study the online binary sequential calibration problem. A recent breakthrough by itet{dagan2024breaking} overcomes the classical (T^{2/3}) barrier fo
arXiv:2607.12884v1 Announce Type: new Abstract: Patients seeking medical information often ask questions that embed incorrect assumptions or misconceptions. In such cases, safe medical communication r
arXiv:2512.01241v4 Announce Type: replace-cross Abstract: Large language models (LLMs) and medical AI tools are routinely used by physicians and patients for medical advice, yet their clinical safety
arXiv:2607.12204v1 Announce Type: new Abstract: Attention can be viewed as an online learner over context, yet existing test-time memories cannot certify that dropping a token leaves outputs unchanged
arXiv:2607.12982v1 Announce Type: new Abstract: Math reasoning has achieved significant progress with the rapid advancement of Multimodal Large Language Models (MLLMs), however analytic geometry remai
arXiv:2607.12260v1 Announce Type: new Abstract: Early screening of chronic kidney disease (CKD) is essential for preventing irreversible progression; however, many machine learning (ML)-based screenin
arXiv:2607.11978v1 Announce Type: cross Abstract: Precision molecular design aims to discover personalized drug candidates through joint control of multiple conditions, such as biological relevance an
arXiv:2607.12077v1 Announce Type: new Abstract: Multi-agent language-model systems increasingly route local interactions, yet the runtime interaction graph is often treated as an implementation detail
arXiv:2607.11951v1 Announce Type: new Abstract: Large language models can write SQL, but enterprise deployment demands more than plausible text: outputs must be syntactically valid, must respect per-r
How I tricked Claude into leaking your deepest, darkest secrets I've been impressed by the way the Claude web_fetch tool is designed to avoid data exfiltration attacks. Ayush Paul found a hole in that
arXiv:2607.11942v1 Announce Type: cross Abstract: KV-cache compression methods are predominantly evaluated with the query appended to the context before compression -- a query-aware protocol. Yet the
Deploying the Gemini Enterprise app across an organization marks a transformative leap forward in workforce productivity, providing employees with an amazing, high-performance suite of agentic AI tool
arXiv:2607.11906v1 Announce Type: new Abstract: The development of decision-pretrained transformers, algorithm distillation, long-context meta-RL, and retrieval-augmented agents has renewed interest i
arXiv:2607.12630v1 Announce Type: cross Abstract: Visual Language Navigation (VLN) aims to enable an embodied agent to navigate complex environments by following natural language instructions. Recent
arXiv:2607.12625v1 Announce Type: new Abstract: OpenClaw has emerged as a leading agent framework for complex task automation, yet it faces insufficient cross-platform GUI interaction support and a we
arXiv:2603.13356v2 Announce Type: replace Abstract: Robust reinforcement learning typically assumes that feedback sources are either globally trustworthy or corrupted within a fixed global budget. We
The full quote: I realize that some people really dislike AI, but this is an area where I'm willing to absolutely put my foot down as the top-level maintainer. Linux is not one of those anti-AI projec