Knowledge catalogue
Research: A shot-scraper-style JSON API on Bun 1.4's new Bun.WebView Today saw the long awaited release of Bun 1.4, the first stable version since the infamous Rust rewrite a few months ago. Interesti
arXiv:2608.18819v1 Announce Type: new Abstract: Graph neural networks (GNNs) are widely used, but how parameter sparsity affects the expressivity of relational (RGNNs) and temporal (TGNNs) variants is
arXiv:2608.18093v1 Announce Type: cross Abstract: Abliteration, the removal of refusal capabilities from large language models by projecting weight matrices orthogonal to an extracted refusal directio
AI did not suddenly discover a cancer vaccine. That is engagement bait. Moderna and Merck reported positive Phase 3 results for Intismeran plus Keytruda in 1,137 melanoma patients after surgery. This
AirLLM dramatically reduces inference memory usage, letting 70B large language models run on a single 4GB GPU card — without quantization, distillation, or pruning. You can even run 405B Llama 3.1 on
Hi all, it is my very first post, because I am so confused. First my setup: I have 2 X 7900XTX with rocm7.2.1 and I use it to fine tune small models and local llm etc. I run Qwen 3.8 27b 8 bit version
arXiv:2608.18675v1 Announce Type: new Abstract: Accurate forecasting of energy consumption is important for the efficient operation of power systems, with direct implications for operational costs, en
arXiv:2608.18164v1 Announce Type: cross Abstract: Safety evaluations of large language models (LLMs) predominantly rely on text-based adversarial prompts, potentially overlooking vulnerabilities arisi
arXiv:2608.18451v1 Announce Type: new Abstract: extbf{Background and Objective}: Reliable atrial fibrillation (AF) detection from electrocardiogram (ECG) signals remains challenging in real-world clin
arXiv:2608.19004v1 Announce Type: cross Abstract: Site-specific weed management in paddy farming offers substantial reductions in herbicide use over conventional broadcast spraying, but field deployme
Awesome Gemma is live on @github 🤗 A list of awesome Gemma resources, tools, and projects. 1. Model cards and collections for 16 Gemma variants 2. Setup guides for Ollama, vLLM, and LiteRT 3. Fine-tun
server: add dedup-cache-models preset option (#27346) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCF
metal : dequantize q8_0 using packed types (#27370) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFra
mtmd: add mtmd_bitmap_set_mergeable (#27348) Website: https://llama.app macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silicon (arm64, KleidiAI enabled) DISABLED macOS Intel (x64) iOS XCFramework
ggml: add ggml_rope_set_offset (+ metal support) (#27120) add params cpu kernel metal kernel add test backend ops gate other backends ggml: (cuda) support ggml_rope_set_offset (#27121) rm cuda support
model : GraniteSWAForCausalLM / GraniteMoeSWAForCausalLM (#25505) feat(convert): Add conversion for GraniteSWAForCausalLM Branch: GraniteSWAForCausalLM AI-usage: full (Bob, OpenCode + Qwen3.6-35b) Sig
vulkan: add null checks in ggml_vk_queue_command_pools_cleanup (#27353) Guard against null queue pointers. Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/4
vulkan : dequant q8_0 KV once in coopmat1 (#25494) vulkan : dequant q8_0 KV once in coopmat1 Assisted-by: Claude (Opus 4.8) vulkan : fall back instead of aborting when FA scratch exceeds maxStorageBuf
server: refactor sleep handling, allow access /metrics during sleep (#27376) add cached responses refactor on_sleeping_state allow accessing metrics during sleep metrics task should not reset timer up
ggml-cpu: gate __fp16 on __ARM_FP16_FORMAT_IEEE (#26860) ggml-cpu: gate __fp16 on __ARM_FP16_FORMAT_IEEE __ARM_NEON only signals NEON availability. The __fp16 type also needs the IEEE half format, imp
https://omlx.ai/benchmarks/performance/2pko3m1k - you can expand the raw args, but I have full annotations of what worked and what didn't. I'm now testing the model on acutal coding and haven't seen a
arXiv:2608.18575v1 Announce Type: new Abstract: Large language model (LLM)-based multi-agent systems (MAS) often exhibit complex failure modes, which frequently cause agents to produce incorrect outco
arXiv:2608.19181v1 Announce Type: cross Abstract: On-policy distillation (OPD) trains a student on its own responses using dense token-level guidance from a stronger teacher. In long-context tasks, ho
arXiv:2608.19161v1 Announce Type: new Abstract: Language-model agents can communicate through continuous hidden states that are invisible in public transcripts, creating opportunities for covert harmf
Jagmeet Singh / TechCrunch: Binance launches Agent OS, a platform that lets AI agents analyze markets and execute trades on users' behalf; users set limits on AI agents' access and trades — Binance, t
Marcela Ayres / Reuters: Brazil announces ~444.2M in AI investments split between US and Chinese companies, including ~250.3M for a supercomputing project with Huawei and iFlytek — Brazil's government
BREAKING: Grok 4.6 just tied for #1 on the Artificial Analysis Agentic Index.⚡🤖 • Grok 4.6 (High) — 59 • Claude Opus 5 (Max) — 59 Grok 4.6 is now at the top of the benchmark, ahead of other leading mo
arXiv:2608.18938v1 Announce Type: new Abstract: Vision Language Models (VLMs) have recently emerged as a critical component of multimodal AI systems, enabling joint reasoning over visual and textual i
arXiv:2608.18723v1 Announce Type: cross Abstract: Telecom operators traditionally offer predefined tariff grids, forcing users to choose from a limited set of plans. This paper proposes BFTR (Budget-F
arXiv:2608.18261v1 Announce Type: new Abstract: Serving a 235B-parameter Mixture-of-Experts (MoE) model on a single 8 GB GPU is bottlenecked not by compute but by memory bandwidth: decode must stream
arXiv:2608.18710v1 Announce Type: new Abstract: Recent advances in generative video models have enabled camera-controlled world video generation, allowing models to synthesize videos under user-define
arXiv:2608.18591v1 Announce Type: new Abstract: Uniformly allocating inference reasoning budgets to LLMs is expensive and prone to over-thinking penalties; especially in document tasks where visual la
arXiv:2511.22842v3 Announce Type: replace-cross Abstract: Causal machine learning (Causal ML) aims to answer 'what if' questions using machine learning algorithms, making it a promising tool for high-
ChatGPT search now uses the site:operator at scale Promptwatch is part of the emerging 'GEO' space, for Generative Engine Optimization - the chatbot version of SEO, where companies offer tools and con
arXiv:2608.19165v1 Announce Type: new Abstract: ChildSafeAds is a shared task on commercial content in YouTube videos likely to reach children and teenagers. It contains 3,360 videos from 939 channels
arXiv:2608.18734v1 Announce Type: new Abstract: 4D understanding and reasoning is a fundamental capability for embodied AI agents operating in dynamic physical environments. However, existing vision e
Claude's skill creator (literally, just ask it to make a skill) is still the best way to make reusable skills if you care about the details. ChatGPT tends to want to do magic & just do it for you, whi
arXiv:2608.18242v1 Announce Type: new Abstract: We introduce ClosureBench, a constructive benchmark for compositional graph-relational reasoning with programmatically verified ground truth. Unlike fix
arXiv:2608.18719v1 Announce Type: new Abstract: Text-space skill optimization adapts a frozen agent by evolving a natural-language skill document, accepting each candidate through a validation gate. E
arXiv:2608.18307v1 Announce Type: new Abstract: Current evaluation of computer-use agents is split between long-horizon workflow benchmarks and atomic GUI-grounding tests. This leaves an under-instrum
arXiv:2608.18578v1 Announce Type: new Abstract: Proactive interference (PI) is a documented failure mode in large language models in which retrieval of a repeatedly overwritten value degrades as prior
arXiv:2608.18660v1 Announce Type: new Abstract: Collaborative virtual reality (VR) environments make team communication observable as it unfolds, but conventional transcript analyses often summarize e
arXiv:2608.18100v1 Announce Type: cross Abstract: AI systems now shape how hundreds of millions of people learn about cultures other than their own. When someone asks one of these systems about the Mi
Congratulations to the whole @GoogleDeepMind Gemma team! Gemma is one of the most popular open models. It's been an amazing journey being a close partner! Can't wait to see what's to come! 🎉 Gemma off
arXiv:2608.18613v1 Announce Type: new Abstract: Cyber threat intelligence (CTI) is increasingly consumed not by human analysts but by LLM agents that compose multi-step investigations at query time. T
arXiv:2608.18795v1 Announce Type: cross Abstract: Majority voting over multiple LLM samples is widely used to raise answer accuracy, yet its gain varies erratically: on hard questions it can even back
arXiv:2608.18103v1 Announce Type: cross Abstract: Background: Mechanistic elucidation of traditional Chinese medicine (TCM) compound formulas remains a central challenge in the modernization of TCM. C
arXiv:2608.18988v1 Announce Type: cross Abstract: Retrieve-then-generate pipelines are commonly used to produce deep-research answers for open-ended questions, but retrieval alone is insufficient: LLM
Coinbase CEO Brian Armstrong recently posed the question every company scaling AI is asking: how do you keep spend flat while token usage grows exponentially? This isn’t hypothetical. It’s confronting
IQ quants are particularly slow on CPU at large batch sizes (what you'd see for imatrix and perplexity) Benchmark numbers I ran PPL against master and this PR to get speed and numbers on --chunks 50 f
arXiv:2608.18142v1 Announce Type: new Abstract: It is challenging to detect hate speech in Low Resource Languages (LRLs) because of the absence of annotated data, the informality of its language struc
arXiv:2608.18083v1 Announce Type: new Abstract: Understanding language requires tracking entities across discourse - i.e., knowing where things are and how they change, even when not explicitly stated
arXiv:2608.18469v1 Announce Type: cross Abstract: Lightweight proxy models enable rapid experimentation without repeatedly training frontier-scale systems, but their small kernels often leave modern a
arXiv:2602.05887v3 Announce Type: replace Abstract: Low-rank matrix sensing is a fundamental yet challenging nonconvex problem whose optimization landscape typically contains numerous spurious local m
arXiv:2608.18289v1 Announce Type: new Abstract: The extraction of structured information from unstructured documents represents a critical component of digital transformations in all sectors. While pr
arXiv:2608.18632v1 Announce Type: new Abstract: Aerial nadir video combines weak geometric constraints with severe perceptual aliasing, making it a difficult regime for monocular SLAM. We benchmark fi
arXiv:2605.06185v2 Announce Type: replace Abstract: Large vision-language models perform well on short- and medium-length video understanding but still struggle to maintain coherent event memory and r
arXiv:2608.18726v1 Announce Type: new Abstract: Large language models are increasingly used for quantitative work in the environmental sciences, yet existing evaluations score only final answers, leav
Since announcing Google Antigravity in Gemini Enterprise Agent Platform at I/O in May, we’ve heard helpful feedback from our customers. Your developers want easy access to coding agents across surface
arXiv:2508.13068v2 Announce Type: replace Abstract: Medical vision-language models still struggle to match radiologists' attention and to verbalize findings with explicit spatial grounding. We address