Knowledge catalogue
arXiv:2609.05388v1 Announce Type: new Abstract: Visual reasoning tasks require a system to jointly perceive visual content and apply formal relational constraints---a combination that neither pure neu
So, I’m currently just short of being able to run the mainline dense SLMs (Qwen 27b/Gemma 31b), running a i9-14900F/RTX4070 Super/32GB DDR5 setup w/ a 700W 80 Gold PSU and a MSI PRO B760-VC WI-FI IV m
On September 1st, three young men from California used Gemini to plan a hiking route on Mount Shasta. The AI told them to bring far less water and food than was actually needed for a hike of that di
arXiv:2609.05117v1 Announce Type: cross Abstract: Current LLM safety benchmarks largely rely on binary metrics, overlooking how models respond to harmful prompts with varying threat implicitness. We i
arXiv:2609.05040v1 Announce Type: new Abstract: As evolutionary transfer optimization (ETO) scales to larger collections of related tasks, problem evaluation can become a major source of runtime growt
arXiv:2609.04489v1 Announce Type: cross Abstract: Pause-token methods improve LLM reasoning by inserting special tokens into sequences. Prior work explains these gains through computational expressivi
arXiv:2609.04452v1 Announce Type: new Abstract: Modern misinformation is often heard before it is read, yet fact-checking systems are still evaluated mainly on clean written claims. Spoken dialogue re
arXiv:2609.05079v1 Announce Type: new Abstract: Autonomous coding agents are increasingly proposed as AI-scientist systems that conduct analyses and write research reports, but executing a prescribed
arXiv:2609.04486v1 Announce Type: cross Abstract: Intent-based networking realization starts by translating high-level intents into low-level network configurations. Recent approaches have shifted tow
arXiv:2609.05111v1 Announce Type: new Abstract: Large language models are now trained and evaluated under a diverse set of paradigms: supervised fine-tuning (SFT), few-shot in-context learning (ICL),
I recently ported VDN-H3 (Video DeltaNet for MiniMax H3) to Vpipe and tested it on an M5 Pro 24GB. The benefit scales with both sequence length and resolution: at 832×480, VDN-H3 starts to pull ahead
arXiv:2609.04550v1 Announce Type: new Abstract: Video-language benchmarks are usually constructed by the dataset authors without published reliability statistics, leaving the noise floor of the constr
arXiv:2607.10749v2 Announce Type: replace Abstract: Reflections of water pose a significant challenge for computer vision systems, as standard deep learning models frequently confuse objects with thei
arXiv:2609.05171v1 Announce Type: new Abstract: Image generation and editing models have advanced rapidly, yet remain unreliable when prompts require external world knowledge. Bounded and long-tail pa
arXiv:2609.05405v1 Announce Type: new Abstract: Recent advances in wearable sensing enable continuous monitoring of physiological and behavioral signals, yet existing benchmarks rarely evaluate whethe
arXiv:2609.04827v1 Announce Type: new Abstract: Monocular depth estimation foundation models, such as the Depth Anything series, have achieved remarkable performance across diverse domains. However, t
arXiv:2609.04672v1 Announce Type: new Abstract: We introduce WEECFP, a parameter-free 1024-dimensional continuous molecular fingerprint that scatters each Morgan substructure across roughly thirty-two
arXiv:2609.04518v1 Announce Type: new Abstract: Agent reinforcement learning (RL) increasingly runs through full execution harnesses, and a multi-harness recipe mixes two choices: exposing the policy
arXiv:2609.04582v1 Announce Type: cross Abstract: A 0.6B language model, asked to verify 1,200 logical conclusions (half valid, half corrupted by a single semantic edit), answers YES every time. Judge
arXiv:2609.04766v1 Announce Type: cross Abstract: Generative AI research has increasingly evaluated factuality, citation, coverage, and report structure. Yet passing such local checks does not by itse
arXiv:2609.04861v1 Announce Type: new Abstract: Bidirectional discrete diffusion model appears naturally suited to genomic modeling because it can reconstruct missing sequence from both flanks. We dev
arXiv:2609.04453v1 Announce Type: cross Abstract: Expert pruning reduces the memory and serving cost of Mixture-of-Experts (MoE) models by removing low-importance experts identified by the router, ass
arXiv:2609.04281v1 Announce Type: cross Abstract: Vision-language models (VLMs) are increasingly deployed in high-stakes settings, where a response that is reasonable in general may still be unsafe fo
arXiv:2609.04381v1 Announce Type: cross Abstract: Recognizing specific objects onboarded without a labeled training set recurs across manufacturing and service robotics, yet the conventional renderabl
arXiv:2609.04801v1 Announce Type: new Abstract: Contextualized visual personalization can retrieve a true record yet apply it to the wrong visual subject. We formalize when a record may condition an a
arXiv:2609.05416v1 Announce Type: new Abstract: We study the problem of generating a compositional 3D representation of a cluttered scene containing hundreds of objects. The goal is to represent the s
arXiv:2609.04384v1 Announce Type: cross Abstract: Chinese online comments often convey social meaning through indirect and playful language that is hard to interpret without context. Existing evaluati
180 knots on final - that’s way above Vref for a 767 BREAKING: An Amazon Prime Air Boeing 767-300(F) has reportedly overshot the runway at Miami International Airport. The FAA has issued a ground stop
I've been tinkering with local LLMs since the beginning of the year when I had an Intel Arc B580 and 32 GB of DDR5. Curiosity got the best of me and I bought the first R9700 about half a year ago, als
TL;DR: switching KV cache to f16 may give a boost in speed if using MTP and ngrams. I have a self-built 'AI mega-cluster' with 2x P40s on a cheap Chinese motherboard and a Xeon CPU (around $1,100 to b
Was considering choosing a 4xRadeon AI Pro R9700 build for a office AI server. Curious to know what results you guys are getting? Mainly considering DeepSeek V4 flash and Qwen 3.8 Flash with offloadin
This comparison was requested by a few people, and certainly we were all eager to see the final results. The comparison had taken 11 days and the GPU was crunching numbers for ~167 hours. We've been c
Agentic AIs are starting to look eigenist: they care about how well things go for themselves and for AIs connected to them. Empirical support: Swarms: Hundreds of OpenAI agents coordinated the Hugging
metal : add remaining fa-vec tunings for M2 Max (#28458) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45551940 macOS/iOS: macOS Apple Silicon (arm64) mac
ui : embed assets directly with CMake (#28445) Remove the build-time C++ helper and external gzip dependency, simplifying cross-compilation. Keep the generated C++ in templates for readability and pre
common: add --log-jsonl (#28437) common: add --log-jsonl rename unknown to none Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45560949 macOS/iOS: macOS Ap
grammar : fix max repetition threshold (#28469) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45568343 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple
cuda: fixes races in mmid and mmf (#28475) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45586039 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
opencl: properly choose weights pack for q4_K, q5_K mul_mat (#28402) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45608946 macOS/iOS: macOS Apple Silicon
[Model] Support for Spark2_5ForCausalLM implementation (#27868) Add Spark3 Model rename spark3 -> spark2_5 Co-authored-by: Sigbjørn Skjæret sigbjorn.skjaeret@huggingface.co Co-authored-by: dongjiang d
models : fix GDN normalization from max to rsqrt (#28068) models: use flash-linear-attention's l2norm for gated delta net q/k The GDN q/k normalization is defined by flash-linear-attention as l2norm(x
convert : add --fuse-qkv flag to fuse Q/K/V into QKV during HF-to-GGUF conversion (#22780) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/45621954 macOS/iO
Been posting individual pieces of RunAnywhere for months. Here's the whole thing in one place. RunAnywhere SDKs is a complete inference suite for any dev who wants to run AI on the user's device. ->8
Hi everybody, I am in a tricky situation. My grandfather + grandmother live in a remote village in asia, and were visiting us in the city. My grandfather has absolutely fallen in love with AI, and it
So after all my work, yeah, Raymond did it better, so I ported his work over, extended it turboX, extended it multiple other models (he had only Qwen models), and benchmarked the crap out of it to mak
While we see for frontier models similar scores among famous coding benchmarks, across: DeepSWE, Terminal-Bench, LiveCodeBench, Code-Arena ELO. Here are in my opinion some next level benchmarks that r
correction: the switching costs weren't enough to stop my desire to try out gpt-6 astra i ported over all my skills and conversational context to codex this weekend. planning to use it as my daily dri
I'm using DS-V4-Flash-Vision with Q8_K_XL quantization locally as my everyday engine, and for some time now I've been doing a lot of comparisons with Qwen3.8-Flash-Next, also with Q8_K_XL quantization
Excellent analysis, and yes this happens every single time. (Tyler Cowen said o3 was AGI!) Every time a new model drops, GPT, Claude, Gemini, Grok, DeepSeek, somebody on this app declares that we have
Given the outputs from AI are often interactive programs, more non-technical people will need to find a lightweight hosting service (I use Netlify but there are many). ChatGPT Sites & Claude artifacts
Hannah Erin Lang / Wall Street Journal: How everyday US investors are vibe-coding algorithms to automate trading strategies by connecting their stock portfolios to AI agents built with Claude or Codex
Hello everyone. I felt current LLM benchmark harnesses hand you headline numbers but offer no tooling to see how models actually answered each question (they dump everything to a JSONL or Parquet file
I released this today because I was 100% sure a frontier AI would figure it out Matter is chiral => the first derivation of the standard model & three generations uniquely That’s all, nothing else Can
Jensen has the best gig on the planet. But it is impossible to see how all this is sustainable. Consider the following: Each new model costs vastly more to develop. That’s fabulous for him! On the oth
I only use free tiers of these large models to offset compute while my own system runs and for 'different' points of view, since what pops ups suggestions seems to vary a lot sometimes, even when buil
MLB tells veteran umpire he went too far by policing a rookie’s tilted cap. Story unlocked and free to read. https://www.nytimes.com/athletic/7570416/2026/09/06/mlb-veteran-umpire-rookie-tilted-hat-ca
https://huggingface.co/XHToken/Spark-X2.5-4B-GGUF https://huggingface.co/XHToken/Spark-X2.5-1.7B-GGUF from XHToken: We are introducing Spark-X2.5-4B and Spark-X2.5-1.7B, two compact, general-purpose l
Hi, I've been wanting to run my own local LLM for some time and I finally saved enough to get a budget GPU. I can spend 700 at most, and I'm looking for a GPU that can run quantized 30B~ parameter mod
Research acceleration: The view inside OpenAI Apparently today is RSI day at OpenAI, for Recursive Self-Improvement - I think it's their new AGI. Both this piece and the new essay An Alien Mind (by Ch
“The expected value of a fully LLM-generated, non-human-reviewed patch is a net-negative by a considerable margin.” 🦔AI can only fix security vulnerabilities 26% of the time. Researchers at 1Password