Knowledge catalogue
arXiv:2610.06672v1 Announce Type: new Abstract: Long-video understanding places substantial demands on memory, as answering questions often requires retrieving information distributed across extended
arXiv:2610.05095v1 Announce Type: cross Abstract: Latent Dirichlet Allocation (LDA) and models derived from it remain widely used topic models. LDA observes each document as a bag-of-words and models
arXiv:2610.05700v1 Announce Type: new Abstract: Recurrent sequence models must decide how strongly to overwrite their memory at each token. Read as Bayesian filtering, this write is the gain of a Kalm
arXiv:2610.04536v1 Announce Type: new Abstract: Underwater manipulation couples visual decisions, contact forces and a thruster-controlled floating base. We introduce WasserMan, to our knowledge the f
arXiv:2610.04151v1 Announce Type: new Abstract: Content-provenance standards such as C2PA let a platform recover a stripped manifest through a soft binding: an invisible watermark read from the conten
We are releasing the only Western OSS LLM that is competitive with the best Chinese OSS models for coding tasks! Mistral Large 4 preview, AKA le Chonk 🐈 is SOTA OSS on cyber and human evals. Check 🧵 b
arXiv:2610.05865v1 Announce Type: new Abstract: Feature pyramid methods, from FPN to BiFPN, have achieved strong performance in face detection by fusing multi-scale features. However, detecting faces
arXiv:2610.04533v1 Announce Type: new Abstract: Weight decay is widely used as a regularization technique in neural network training, yet its role in neuron condensation (parameter direction alignment
We’re releasing a broad range of new mathematical results produced by an internal frontier model. We’ve been consulting with the independent Advisory Group on Mathematics and Artificial Intelligence a
We’re so back. Meet Mistral Large 4, aka Le Chonk. • 1T parameters, natively multimodal. 49B active. It is the best open weights model from US or Europe on aggregated benchmarks. • State-of-the-art on
arXiv:2610.03792v1 Announce Type: new Abstract: Reinforcement learning from verifiable rewards (RLVR) has produced large reasoning gains in language models, and verifiable video benchmarks make it app
arXiv:2610.04433v1 Announce Type: cross Abstract: A coding agent is a language model wrapped in a harness: the system prompt, the tool set, and the context management that turn a chat model into somet
arXiv:2610.05533v1 Announce Type: new Abstract: Harness search keeps a change to the prompts, reasoning switches, token budgets or parsers around a frozen model if the change raises a score. Such a ga
arXiv:2610.05577v1 Announce Type: new Abstract: A linear probe can show that a label is recoverable from a model's hidden states, but not whether that goes beyond what the input already reveals, or wh
arXiv:2610.06176v1 Announce Type: cross Abstract: Near-term quantum natural language processing (QNLP) experiments often run on classical simulators, so simulator cost is part of the field's practical
arXiv:2610.04128v1 Announce Type: cross Abstract: Split learning lets a client train a language model on a server without sending its text. The client runs the first layers itself and sends the server
arXiv:2610.04303v1 Announce Type: new Abstract: Recursive computation repeatedly compresses or reuses intermediate states, creating a simple tension: information that must remain useful across longer
arXiv:2610.04978v1 Announce Type: new Abstract: Data selection, curricula and the evaluation of post-training recipes all assume that we can tell, before training, which problems a model will improve
arXiv:2610.05322v1 Announce Type: new Abstract: Test-time compute can improve mathematical reasoning, but can short-budget runs predict how mathematical reasoning scales with additional compute? We in
arXiv:2610.05492v1 Announce Type: new Abstract: Vision-language-action (VLA) models have shown strong potential as generalist robot policies, but adapting them to unseen tasks often requires costly pa
arXiv:2610.04756v1 Announce Type: cross Abstract: Self-evolving large language model (LLM) systems repeatedly propose, evaluate, and incorporate updates to prompts, skills, or other persistent artifac
Across the public sector, the question has shifted from “what’s possible?” to “how can we drive mission impact?” We’ll be answering this question at the Google Public Sector Summit on October 20th at
Over the past several months, we conducted an empirical post-mortem investigation into 109 autonomous AI agent security incidents (cataloged with 193 falsification criteria across tool-use and multi-a
arXiv:2610.04073v1 Announce Type: new Abstract: Recent advances in attention-based deep learning have motivated their adoption for remote sensing image classification; however, their benefits for cryo
arXiv:2610.04907v1 Announce Type: new Abstract: Subliminal learning lets a student inherit a teacher's behavioral trait from semantically unrelated data, yet published demonstrations typically require
will Anthropic’s IPO be based on its best quarter, or reality? Microsoft has cut internal Claude spending by over a third, and Meta's Claude Code users have halved. - per The Information 'Microsoft wa
arXiv:2610.05341v1 Announce Type: new Abstract: Chronic wound management affects over 8.2 million patients in the United States and imposes substantial clinical and economic burden. Clinical wound ass
arXiv:2610.06318v1 Announce Type: new Abstract: Dense affordance supervision is an appealing auxiliary signal for vision-language-action (VLA) policies, yet naively co-training an affordance head can
arXiv:2610.06509v1 Announce Type: new Abstract: Deep learning has revolutionised weather forecasting in recent years, especially through atmospheric foundation models, which offer competitive skill fo
arXiv:2407.18137v2 Announce Type: replace Abstract: Small object detection and tracking in videos remain critical yet underexplored challenges in computer vision, particularly for applications such as
You can now run Clef via llama.cpp! llama serve -hf ggml-org/Clef-GGUF Ollama vs llama.cpp speed test on my M5 Max MBP: The new v0.6.0 release packs a lot of good stuff: - Clef support (text + vision)
arXiv:2610.03715v1 Announce Type: cross Abstract: We introduce 4DCodeBench, a benchmark for 4D inverse graphics through code generation, in which agents reconstruct dynamic scenes from video as execut
A while ago, I posted here getting OSS-120B and GLM-4.6 playing full games of Civilization V. Since then, models have moved pretty far, and we wanted a better understanding about models' capabilities
arXiv:2610.03105v1 Announce Type: new Abstract: Communication in shared space interweaves verbal and non-verbal signals, and pointing gestures anchor language to the environment: 'put the cup on that
arXiv:2610.02764v1 Announce Type: new Abstract: In structured rating prediction, does a personal AI use historical item-rating associations, or mainly the user's rating tendencies? We audit this disti
arXiv:2610.02439v1 Announce Type: new Abstract: Generative graph models are central to understanding and simulating complex networks. However, existing approaches have complementary strengths and limi
arXiv:2610.02664v1 Announce Type: new Abstract: Long-horizon agents are now playing an increasingly significant role in assisting humans with complex problem-solving. However, it is exactly their exte
arXiv:2610.02970v1 Announce Type: new Abstract: Large language models (LLMs) have shown promising potential for biomedical named entity recognition (BioNER) through instruction following and in-contex
arXiv:2610.03468v1 Announce Type: new Abstract: Editable 3D models of field-grown crops support high-throughput phenotyping and in silico breeding trials, but building them from scanned point clouds r
arXiv:2610.02856v1 Announce Type: new Abstract: Multi-task post-training of large language models (LLMs) aims to improve performance across tasks with unequal amounts of training data. Existing method
arXiv:2610.02822v1 Announce Type: cross Abstract: Temporal Domain Generalization (TDG) has emerged to address real-world streaming data with distribution shifts over time. However, existing methods ar
Hi r/LocalLLaMA. I'm on the team at Blockway, a small team in Hong Kong (disclosure: this is our model). Today we released Agens Volundr 32B Preview, the first model built on our own hybrid architectu
arXiv:2610.02661v1 Announce Type: new Abstract: Real-time data streams in Web of Things (WoT) and edge computing environments often evolve through latent regime changes. For online representation lear
arXiv:2610.02835v1 Announce Type: new Abstract: During post-training of large language models (LLMs) with Reinforcement Learning with Verifiable Rewards (RLVR), GRPO-style algorithms can exhibit sever
arXiv:2610.03505v1 Announce Type: new Abstract: Post-exposure microscopy is central to qualification of fusion materials. However, manual analysis does not scale to the volume, heterogeneity, and mult
arXiv:2610.03078v1 Announce Type: new Abstract: Quantifying conversational dynamics requires reliable identification of interactional units and their temporal boundaries, but speech activity alone doe
BBC: An official says the DOD has stopped using Anthropic's tools; sources: Claude was in use as recently as last week, including in military operations against Iran — Technology reporter in San Franc
SemiAnalysis: Analysis: Anthropic's subscriptions offer ~5x more API-equivalent value per month than OpenAI's for agentic workloads with Claude Opus 5.5 vs. GPT-6.1 Sol — Limit testing every AI subscr
arXiv:2610.02770v1 Announce Type: new Abstract: Document databases such as MongoDB are core infrastructure for modern applications, and natural-language interfaces to them---text-to-MQL---would let no
arXiv:2610.02438v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong performance in code generation, where success depends on both recalling relevant algorithmic kno
arXiv:2610.02728v1 Announce Type: new Abstract: Closed-loop learned locomotion is established on commercial quadrupeds but remains uncommon at the sub-kilogram scale. Continuous-rotation legs give MiN
arXiv:2610.03102v1 Announce Type: cross Abstract: An LLM agent can recognize uncertainty yet still choose the wrong next step: asking when action is already justified, or seeking clarification when th
arXiv:2610.02775v1 Announce Type: new Abstract: Mental health stigma has profoundly harmful impacts but its complexity makes it difficult to evaluate. Stigma may involve explicit derogation, but also
arXiv:2610.02369v1 Announce Type: cross Abstract: Human-computer interaction (HCI) is in the middle of a transition: large language models can now generate functional user interfaces (UIs) on demand f
llama: support both embd + raw tokens in batch (#29622) llama: support both embd + raw tokens in batch add to test-llama-archs also check case llm_arch_supports_mixed_batch = false constant graph topo
log, server: self contained colors, split child commands from logs in router mode (#29895) log, server: make router child lines carry their own colors The logger writes the color reset after the trail
CUDA: prefer whole-tile FlashAttention scheduling for efficient two-stage kernels (#29435) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/52707115 macOS/iO
CUDA: use MMVF for thin f16/bf16 mul_mat at small batch size (#29633) CUDA: use MMVF for thin f16/bf16 mul_mat at small batch size Signed-off-by: ynankani ynankani@nvidia.com adjust kernel selection l
metal : few-row MMA mat-mul (#29869) metal : few-row MMA mat-mul and batched copies for speculative decoding Speculative decoding verifies a few draft tokens per step. Without the tensor API, Metal ra
cuda: tile the lightning indexer over keys and tokens for 4 heads (#29901) cuda: tile the lightning indexer over keys and tokens for 4 heads With too few heads for a wmma tile, a block scores 64 keys