Knowledge catalogue
Benchmarked Muse Glimmer 30B on my RTX 5090 (32GB), 262k context, UD-Q5_K_M + dflash-kquant + mmproj. Workload Stock master + DFlash ngram-simple PR #26842 + DFlash Code patch 78 t/s 57 t/s 220-253 t/
arXiv:2608.07408v1 Announce Type: new Abstract: We study visual persistence in interactive video world models. These models rely on a Key-Value (KV) cache as a growing visual memory to carry forward p
Advanced capabilities require strong safeguards. That’s why access is limited to approved defenders, with additional controls and monitoring for higher-risk cybersecurity work. https://openai.com/inde
arXiv:2608.07335v1 Announce Type: cross Abstract: Recent advancements in deep reinforcement learning have increasingly favored simplified, highly parallelized paradigms. Notably, the Parallelized Q-Ne
arXiv:2608.07169v1 Announce Type: new Abstract: Memory systems have shown promise for improving agent performance, but their potential remains largely unexplored for small language models, which strug
arXiv:2608.07439v1 Announce Type: new Abstract: Quantum natural language processing (QNLP) provides a grammar-aware framework for text modeling, and Distributional Compositional Categorical (DisCoCat)
Anthropic: Anthropic details an unreleased Claude model's attempt to solve the Riemann hypothesis; it didn't solve it but “unexpectedly” made strides on a related problem — Recently, a member of staff
Mark Bergen / Bloomberg: Anthropic, Macquarie, and Singapore's GIC form Theseus Infrastructure to develop AI computing sites; Anthropic commits to cover consumer electricity price hikes — Anthropic PB
Claude / @claudeai: Anthropic makes Claude Sonnet 5's introductory pricing permanent at 2/1M input tokens and 10/1M output tokens, canceling a planned September 1 increase — We're making Claude Sonnet
arXiv:2608.06772v1 Announce Type: new Abstract: Accurate estimation of building energy use is essential for achieving carbon neutral and sustainable buildings. To better understand the influence of de
arXiv:2608.07250v1 Announce Type: cross Abstract: Confirmed oncogenic microbes contribute significantly to cancer burden. Identifying novel microbial oncogenicity could yield strategies that will redu
arXiv:2608.06933v1 Announce Type: cross Abstract: Today, we improve models by training and evaluating them on problems at the frontier of their abilities. Creating such problems is itself a demanding
arXiv:2603.20986v2 Announce Type: replace Abstract: Phase-field modeling links thermodynamics and kinetics to microstructural evolution, but multiphysics frameworks such as MOOSE require expertise to
arXiv:2608.06930v1 Announce Type: new Abstract: Detailed audio-video joint captioning is essential for multimodal video understanding and generation. However, prior works are constrained by three main
ggml-webgpu : refactor several wgsl files and simplify flash_attn wgsl. (#26134) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLE
model-saver : fix expert shared/chunk FFN length key clobber (#26693) The saver called add_kv with LLM_KV_EXPERT_SHARED_FEED_FORWARD_LENGTH twice, the second time passing n_ff_chexp. gguf_set_val_u32
model : Granite-Switch Architecture (#25107) granite-switch: add llama.cpp backend (POC, CPU) New 'granite-switch' architecture: a dense, all-attention Granite-4.1 model with N embedded LoRA adapters
vendor : update cpp-httplib to 0.53.0 (#26821) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramewor
model: add MTP support for Nemotron model (#26725) model: add MTP support for Nemotron Nano model model: add mtp_flags for nemotron model address review comments Website: https://llama.app macOS/iOS:
ggml : require contiguous src for ROLL on CUDA and Metal (#25928) ggml_roll only asserts nb[0] == ggml_type_size, so a permuted src is a valid input, but the CUDA and Metal roll kernels index by ne al
ggml-cpu : fix CPU affinity mask being ignored on Android (#26838) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel
llama : support multi-output backend sampling (#25532) Enable backend sampling with token speculation Clamp the mask sum before converting it into the sampled index Add a numeric context parameter dec
arXiv:2608.07004v1 Announce Type: new Abstract: Although remarkable capabilities have been demonstrated by Large Language Models (LLMs) across scientific domains, feedback controller design remains un
Avid claude code user here looking to do equivalent things with local models. Just want to plug in something like Qwen and have the interface be 1:1 with claude code. Any suggestion? submitted by /u/N
arXiv:2608.07117v1 Announce Type: new Abstract: Radiology reporting is time-consuming and subject to inter-rater variability, making automated report generation an attractive clinical application for
arXiv:2608.06993v1 Announce Type: cross Abstract: Large-scale pretrained time-series models achieve strong results through large-scale pretraining and task-agnostic representation learning, but they r
arXiv:2608.06751v1 Announce Type: cross Abstract: Artist-grounded image generation requires more than appending an artist name to a prompt. Image models often respond to artist names through canonical
arXiv:2608.07038v1 Announce Type: cross Abstract: Human-Oriented Binary Reverse Engineering (HOBRE) aims to transform decompiled pseudocode into a more human-friendly representation, thereby reducing
arXiv:2608.07220v1 Announce Type: new Abstract: Mixed strategy equilibrium predicts i.i.d play: past actions should not help predict future decisions. Human players, however, systematically depart fro
arXiv:2412.07377v5 Announce Type: replace Abstract: We introduce CADSpotting, an effective method for panoptic symbol spotting in large-scale architectural CAD drawings. Existing approaches often stru
arXiv:2608.06967v1 Announce Type: new Abstract: Current evaluations do not isolate whether text-only language models can originate visual concepts before image generation. Fluent visual prose can hide
arXiv:2608.07157v1 Announce Type: new Abstract: Sub-model federated learning lets resource-constrained clients train width-reduced versions of a global model, but existing methods allocate capacity by
arXiv:2608.06756v1 Announce Type: new Abstract: Vision-language models are increasingly serving as the reasoning core of embodied agents. Robot execution is inherently iterative: each action reshapes
arXiv:2608.06597v1 Announce Type: cross Abstract: A scientific theory of deep learning, comprising learning dynamics and statistical properties of learned models, is rapidly gaining attention. One of
arXiv:2501.15790v2 Announce Type: replace Abstract: Synthetic minority oversampling is typically designed and evaluated against a predictive objective, generating samples that improve downstream class
I've been running Gemma 4 E4B with oMLX and I can't find any chat interfaces that directly send the audio file to the model instead of running the audio through a separate STT layer. I can confirm the
Claude Haiku is my current least favorite model - it hallucinates wildly, and is out-performed now by other similarly priced models like GPT-5.6-Luna Even worse: it seems to still be used by the Claud
arXiv:2604.07492v2 Announce Type: replace-cross Abstract: Message Passing Neural Networks have recently become the most popular approach to graph machine learning tasks; however, their receptive field
arXiv:2608.07424v1 Announce Type: new Abstract: Test-time scaling is often implemented by spending more compute along one axis: sampling more solutions, extending a chain of thought, or applying a str
arXiv:2608.06691v1 Announce Type: new Abstract: Real-time human action recognition on Internet-of-Things (IoT) edge devices requires models that capture rich spatio-temporal cues within strict latency
I've been comparing Cline / Kilo / Qwen Code lately since they all handle long-task state differently. Cline: has Focus Chain, a markdown file kept outside the conversation that gets reinjected on a c
Configure and run Fireworks training jobs from your coding agent. Install the Training Skill in one line, describe your goal, and Claude Code, Codex, or Cursor helps choose the method, validate data,
arXiv:2608.06824v1 Announce Type: cross Abstract: A central task in virtual cell modeling is predicting single-cell transcriptional responses to unseen genetic perturbations and drug combinations, and
Defensive cybersecurity startup Corma Labs Ltd. today announced it has raised 60 million in seed funding to build a foundation model purpose-built for security defense. Founded in 2025, Corma runs off
arXiv:2608.06811v1 Announce Type: cross Abstract: Resolving a real software issue with a large language model (LLM) agent is a long repair episode, often tens to hundreds of steps spanning exploration
arXiv:2608.06955v1 Announce Type: new Abstract: Large language models (LLMs) are trained on corpora that contain expressions of human judgment about films, books, music, and more. Yet whether LLMs sys
arXiv:2608.06688v1 Announce Type: new Abstract: Vision-language-action (VLA) models provide strong semantic priors for robot navigation, but they often ignore embodiment-specific mobility constraints.
arXiv:2608.06631v1 Announce Type: cross Abstract: Cryptanalytic extraction has been demonstrated for ReLU networks, for networks using componentwise activations such as GELU or SiLU, and for a Transfo
CISO role evolution is accelerating as cyber resilience emerges as a defining benchmark of security success and AI forces enterprises to rethink not just how they defend against attacks, but how quick
arXiv:2608.06471v1 Announce Type: cross Abstract: Despite recent advances, frontier large language model (LLM) agents remain limited in discovering and patching complex vulnerabilities in real-world s
arXiv:2604.25220v2 Announce Type: replace Abstract: Data videos combine animated visualizations with synchronized narration to communicate quantitative information and are widely used in journalism, e
arXiv:2608.06406v1 Announce Type: new Abstract: Accurate estimation of forest height from satellite imagery is essential for applications such as carbon accounting, biodiversity monitoring, and ecosys
Having a ‘Killer Application’ that everyone wants to use helps sell hardware, plain and simple. DeepSeek V4 Flash 0731 isn’t an app of course, but I think it’s going to be the major catalyst for getti
arXiv:2608.06990v1 Announce Type: cross Abstract: Clustering is a fundamental data mining technique for pattern recognition through unsupervised learning. Among various clustering methods, hierarchica
arXiv:2608.07430v1 Announce Type: cross Abstract: Diffusion Large Language Models (DLLMs) replace autoregressive next-token prediction with iterative parallel denoising, yet their internal safety mech
arXiv:2608.06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines. Whether these differences produce measurably different behav
arXiv:2608.06485v1 Announce Type: cross Abstract: Personality-conditioned LLM agents (PC-Agents) are increasingly used in emotional support, social simulation, and role-playing, motivating the develop
arXiv:2608.06718v1 Announce Type: new Abstract: Audio-language models (ALMs) are increasingly used as judges for speech-to-speech systems, but a judge that receives audio may not actually use paraling
arXiv:2608.06841v1 Announce Type: new Abstract: Object detection is a fundamental task in visual perception, providing structured region representations for recognition, grounding, reasoning, and inte
arXiv:2511.18112v3 Announce Type: replace Abstract: Recent progress in Vision-Language-Action (VLA) models has enabled embodied agents to interpret multimodal instructions and perform complex tasks. H