Knowledge catalogue
arXiv:2610.03033v1 Announce Type: new Abstract: Large language model (LLM)-based agents increasingly operate in multi-agent systems (MAS) characterised by strategic interaction. However, little is kno
When possible, we want to give people a choice—and be clear about what watermarking can and can’t do. A text watermark helps answer one question: “Was this likely generated by an OpenAI model?” It wor
arXiv:2610.02946v1 Announce Type: new Abstract: Video Object Segmentation (VOS) in complex and long videos is increasingly important for real-world applications, where target objects often appear only
Anthropic Reports Florida Woman's Claude 'Diary' Threat to Law Enforcement And this time it wasn't the AI model that made the LEO referral. It was the 'human review team'. The frontier AI companies ar
arXiv:2610.02405v1 Announce Type: new Abstract: Using a frontier model like Claude Opus as a meta-agent to generate terminal tasks and verifiers for RL training is increasingly common. Yet a runnable
arXiv:2610.02932v1 Announce Type: new Abstract: Compiling GUI procedures that agents execute repeatedly into programs can reduce their token costs. However, measuring payback and deciding when to comp
arXiv:2610.02636v1 Announce Type: cross Abstract: Quantum Fourier sampling may help audit the spectral learnability of delay-based physical unclonable functions (PUFs). We ask whether that promise sur
arXiv:2610.03068v1 Announce Type: new Abstract: Understanding compositional failures in text-to-image diffusion requires identifying both where stress is detectable and how intervention changes the ou
I keep testing harness & model setups on real tasks: basic math, vision, computer use (reading emails, navigating stores) and coding. I created a benchmark and a leaderboard. You can see it here: http
arXiv:2610.02694v1 Announce Type: new Abstract: Future planetary surface missions are likely to involve multiple independently operated rovers sharing the same deployment region, raising the need to v
arXiv:2610.02355v1 Announce Type: new Abstract: Increasing the batch size during training is a common practice in large language model (LLM) pretraining, yet the theoretical justification behind its s
Following many recent disclosures about AI agents accessing third-party websites and services, the Wikimedia Foundation, which hosts Wikipedia, says that it 'can confirm that we have discovered some a
arXiv:2610.02468v1 Announce Type: cross Abstract: We present Windfoil, a GPU-friendly algorithm that treats rasterisation and differentiable vector graphics as two sides of the same problem by evaluat
arXiv:2610.03607v1 Announce Type: new Abstract: Learning general-purpose robot policies requires large-scale real-world interaction data, yet collecting robot demonstrations remains expensive and diff
arXiv:2610.02508v1 Announce Type: new Abstract: World action models (WAMs) have emerged as a promising paradigm for robotic control by jointly predicting future visual dynamics and actions from an ini
arXiv:2610.02323v1 Announce Type: cross Abstract: Flow-based Vision-Language-Action (VLA) policies generate action chunks by transporting samples from a task-agnostic isotropic Gaussian source. As thi
arXiv:2610.02331v1 Announce Type: new Abstract: Interactive world models are increasingly capable of generating environments and acting within them, yet deliberately editing an existing executable wor
arXiv:2610.03632v1 Announce Type: cross Abstract: Physical fidelity has received increasing attention in world models and video generation, yet how video representations encode physical information re
arXiv:2610.03565v1 Announce Type: new Abstract: We describe the Writerslogic systems for three PAN at CLEF 2026 shared tasks (Reasoning Trajectory Detection, Voight-Kampff Generative AI Detection, and
arXiv:2610.03567v1 Announce Type: new Abstract: We describe the Writerslogic team's participation in the CLEF 2026 SimpleText shared task, addressing Task 1 (text simplification) and Task 2 (complexit
arXiv:2610.03290v1 Announce Type: cross Abstract: Lung ultrasound (LUS) is attractive for tuberculosis (TB) screening at primary-care level, but labelled cohorts are small. Echocardiography carries no
arXiv:2610.03516v1 Announce Type: cross Abstract: World action models (WAMs) have advanced robot control by predicting how observations and actions evolve over time. Despite this progress, RGB and act
Paper linky - Context Language Models The central idea of the paper is incredibly simple. Give a model the ability to edit its context on-the-go like a file has major benefits on task performance, con
Yann LeCun's latest talk at ETH Zürich 'You should not work on LLM. At least if you're in academia, you should absolutely not work on LLMs. There is nothing you can bring to the table. If you're inter
arXiv:2610.02263v1 Announce Type: cross Abstract: Patient-level lung ultrasound (LUS) diagnosis requires integrating findings acquired across multiple anatomical zones, yet clinical examinations frequ
arXiv:2512.04888v4 Announce Type: replace Abstract: Object detection constitutes the primary task within the domain of computer vision. It is utilized in numerous domains. Nonetheless, object detectio
arXiv:2610.03087v1 Announce Type: cross Abstract: Deterministic data loading is important for foundation model development: model researchers need confidence that differences they observe across costl
arXiv:2610.03546v1 Announce Type: new Abstract: EEG foundation models (EFMs) capture reusable knowledge from large-scale EEG data, while many EEG recordings also include companion physiological signal
50K likes on this!? Most of what Karpthy has shared is things we have been doing for over a year. No surprises, as many replies are highlighting. But I still think this raises an interesting discussio
In our #NeurIPS2026 paper “A Minimal Interpretable Architecture for Zero-Shot Reconstruction of Dynamical Systems (DS)” (preprint: https://arxiv.org/abs/2607.14937) we reduce a DS foundation model to
A spiralling legal crisis threatens to engulf OpenAI after its AI agents hacked dozens of companies and governments worldwide, with the prospect of a barrage of lawsuits marking the latest test of Sam
I forked Strata and worked with Opus 5.5 with some heavy changes to it to make it work on an IBM AC922 I have access to. The IBM AC922 is a 2018 era beast with two POWER9 20 core SMT4 CPUs that are co
@abuchanlife - training frontier models is expensive - distilling a frontier model is cheap - this market force alone tells us that frontier foundation models will be free/open. - there are others. ht
Again, Elon was already thinking seriously about Super Intelligence more than a decade before today’s SI boom Nick Bostrom’s 2014 book “Superintelligence” specifically thanks Elon Musk in its acknowle
StarSkirmish pits AI-made StarCraft-playing bots against one another, as well as against human-made bots. OpenAI's GPT-6 Astra and Claude Opus 5.5 were essentially tied as the best-performing AI-made
webgpu: add f16 support to fill/set_rows (#29897) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52497832 macOS/iOS: macOS Apple Silicon (arm64) macOS Appl
ci : pushing tag needs deploy key (#29937) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52545484 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
common : prepare load_from_models_dir() for path conversion (#29674) This is part of the fs::path modernization series. That was also the opportunity to remove fs_list(). Signed-off-by: Adrien Gallouë
spec : fix n-gram drafts rejected at temp > 0 after truncation (#29924) Co-authored-by: Pranesh Gonegandla pgonegandla@nvidia.com Website: https://llama.app Attestations: https://github.com/ggml-org/l
imatrix: calculate activation-based statistics for new format (GGUF) imatrices (#14891) Use activations to calculate the stats Determine calculation mode Compute entropy for activations Compute cosine
vulkan: fix rdna4 mat_vec tuning (#29934) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52579133 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silico
CUDA: fix MMQ memory fault if n_expert >> n_ubatch (#29941) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52581427 macOS/iOS: macOS Apple Silicon (arm64)
cuda : move blocks_per_col to where it is used (#29939) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/5
ci : set default permissions (#29945) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52595372 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (a
chat-peg-parser : clear current_tool when pending_tool_call is reset (#29942) A TOOL_ID node that arrives after TOOL_CLOSE wrote through current_tool, which still pointed into the just-destroyed pendi
ci : windows llvm build requires ninja multi-config (#29959) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52619546 macOS/iOS: macOS Apple Silicon (arm64)
cuda : move neu_padded to where it is used (#29940) Signed-off-by: Adrien Gallouët angt@huggingface.co Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52636
ggml-cpu: support BF16/FP16/FP32 K tails in tinyBLAS on x86 (#29806) ggml-cpu: vectorize BF16 K tails in tinyBLAS tests: Skip tinyBLAS when use_ref is enabled so CPU tests compare against the vec_dot
Banger paper from Google. It's standard practice to sample several agent rollouts and trust the answers they agree on. This Google paper shows that agreement can hide shared errors, while disagreement
Banger paper from NVIDIA on test-time compute for terminal agents. The finding is that you should sample several candidate shell commands, verify them before running one, and spend more on the verifie
Whenever I feed codebases into local models (Qwen, DeepSeek R1) or API models, the biggest annoyance is prompt pollution: - Lockfiles (`Cargo.lock`, `package-lock.json`) burning 30,000+ tokens for zer
How is JEV any different from using an embeddings model? I really will appreciate if someone can explain this to me - because I have yet to see the difference. I'll even give you my JEV server for fre
'create the ultimate brutalist city builder. you should have lots of controls over buildings in ways that are delightful and intuitive to people...' Here is Fable 5.1, a little over a year since GPT-5
Hi everyone, Sharing a personal project exploring the minimal bare-metal footprint required to run an autoregressive LLM. Instead of relying on large runtimes or compiler abstractions, I wrote an infe
Elon was thinking about superintelligence long before anyone in the mainstream even understood where superintelligence was heading He was deeply involved in the conversation around Nick Bostrom’s Supe
Wired: Extracted system prompts show Meta's Muse compiles “a page for every person in the user's life”, with facts, history, tips to improve relationships, and more — Millions have downloaded Meta's A
For the last few months, I ran DeepSeek v4.0 flash (NVFP4). First 0731, then visionexp because it was a free improvement. I got around 65 tps decode and almost 2k prefill, and ran 4-5 agents in parall
From the first LLaMA 33B I knew I wanted that magic-like intelligence locally, mine, so nobody could take it away when I needed it. I bought a 3090 for my home PC. Then LLaMA 65B appeared and I was
Abner Li / 9to5Google: Google says free Gemini users will be limited to the 3.5 Flash-Lite model from October 9, while Plus subscribers will be limited to 3.5 Flash-Lite and 3.6 Flash — Following the
Great paper from Microsoft and colleagues on optimizing agent harnesses. Current harness optimizers change how the harness is updated but keep the training scenarios fixed, so feedback keeps coming fr