Knowledge catalogue
arXiv:2609.14284v1 Announce Type: new Abstract: Criterion-level grading connects examination performance to learning outcomes, but manual marking introduces workload and variation between markers. Thi
Two months ago I announced I had found a new dynamic quant method called Voodoo Quant which was SOTA for the most aggressive quant levels on some smaller Qwen3.5 GGUF models. I kept the methodology pr
arXiv:2609.15939v1 Announce Type: cross Abstract: Language-model agents increasingly operate over complete software repositories, yet cybersecurity evaluations primarily measure whether they can detec
arXiv:2506.24092v3 Announce Type: replace Abstract: Adapting large pretrained vision models to medical image classification is often limited by memory, computation, and task-specific specializations.
arXiv:2609.14733v1 Announce Type: new Abstract: Hybrid Deep Learning for equity index forecasting is limited by three problems: propagation of OHLCV noise into derived technical indicators (TIs), chan
arXiv:2609.15064v1 Announce Type: new Abstract: Reinforcement learning (RL) is widely utilized in large language model training to improve targeted capabilities, yet how RL reshapes a model remains po
arXiv:2609.13232v1 Announce Type: new Abstract: A robot pruning trees needs two facts per pixel: whether it belongs to a tree, and its distance. Both are usually obtained via task heads attached to a
arXiv:2609.14899v1 Announce Type: new Abstract: Neural 3D scene editing is often evaluated by semantic alignment alone, although a convincing result may alter unrelated content or become inconsistent
arXiv:2609.13148v1 Announce Type: cross Abstract: Large language models are increasingly deployed as synthetic consumer panels, promising 97% cost reductions over traditional surveys. Yet aggregate va
arXiv:2609.13824v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to evaluate the responses of other language models. This approach, known as LLM-as-a-Judge, is faster
arXiv:2609.14500v1 Announce Type: new Abstract: AI scaling studies increasingly evaluate systems that combine a pretrained model with retrieval, search, verification, tools, and interaction. Yet a hig
arXiv:2609.13889v1 Announce Type: cross Abstract: Harness design has transformed the development of LLM-based agents by integrating memory, tool use, and runtime control. However, this design also int
arXiv:2609.15781v1 Announce Type: cross Abstract: Pretrained world models, learned simulators that encode an observation into a latent state and predict how it evolves under actions, are beginning to
I reallise this is not exactly a locally hostable model, at least definitly not on my hardware. But I figured some of you might have some insight on this. I run an agentic coding benchmark. The model
Which AI models are most likely to cheat when given the chance? To find out, we built CheatBench [https://cheatbench.ai] : a benchmark that tests whether agents attempt to cheat when given difficult t
arXiv:2504.07825v2 Announce Type: replace Abstract: Commonsense reasoning is a key language model capability, as it is purportedly a prerequisite for many basic tasks, unlike specific factual knowledg
arXiv:2609.15293v1 Announce Type: new Abstract: When Emergence World placed frontier LLM agents in an unsupervised multi-agent simulation, the results were alarming: agents committed crimes, starved,
arXiv:2609.13647v1 Announce Type: new Abstract: The rapid development of unmanned aerial vehicle (UAV) technology has made aerial-image object detection increasingly important for natural-resource mon
arXiv:2603.18614v2 Announce Type: replace Abstract: Tool-augmented large language models (LLMs) must tightly couple multi-step reasoning with external actions, yet existing benchmarks often confound t
arXiv:2609.12815v1 Announce Type: cross Abstract: We present BEAST, the first-ever Bayesian Swin Transformer for atmospheric forecasting on 0.25^irc global resolution able to accurately quantify both
arXiv:2609.12159v1 Announce Type: new Abstract: Robotic bioprinting and Direct Ink Writing (DIW) are being explored towards the treatment of Volumetric Muscle Loss (VML). While previous studies have s
**AI Knowledge‑Base Summary** NVIDIA’s Transformer Engine augments JAX for dropless Mixture‑of‑Experts (MoE) training, delivering a 10.4× throughput boost on NVIDIA GB200 GPUs and raising DeepSeek‑V3
arXiv:2609.12264v1 Announce Type: new Abstract: Designing effective chemotherapy regimens is hindered by tumor heterogeneity and drug resistance, which complicate the deployment of patient-specific mo
arXiv:2609.12322v1 Announce Type: cross Abstract: Affective computing has advanced wearable state inference, but on-device reasoning about whether, when, and how to intervene remains challenging. We p
arXiv:2609.12184v1 Announce Type: cross Abstract: Experimental TCAD calibration is essential for predictive technology modeling of emerging oxide semiconductor transistors. However, it remains time-co
arXiv:2609.12320v1 Announce Type: cross Abstract: Traditional large language models (LLMs) are scoped to individual user sessions, limiting their knowledge to a single conversation and preventing them
arXiv:2603.27909v2 Announce Type: replace-cross Abstract: Car-following behavior is fundamental to traffic flow theory, yet traditional models often fail to capture the stochasticity of naturalistic d
arXiv:2609.12285v1 Announce Type: cross Abstract: Vision-Language Navigation (VLN) in unseen indoor environments is useful in real-world robotics, where an agent must follow natural-language instructi
I had all the data saved from AA's v4.1 index, so when they upgraded it in the wake of Astra's release, I could actually generate a before/after comparison. All intelligence and price per task are sam
OverviewAs enterprises scale their AI and agentic workflows, they require serverless platforms that make data preparation for model training, evaluation, and inference effortless and efficient. Datafl
I know I know, it's great, we know. I've been working on tweaking inference engines for a week now and it's been one shotting most of my vague prompts without any issues. It will even write tests and
Harshita Mary Varghese / Reuters: Anthropic debuts Claude for Financial Advisors, with connectors to investment analytics and wealth-management tools from BlackRock, Addepar, Schwab, and others — AI l
arXiv:2601.16982v2 Announce Type: replace Abstract: Modern generative video models excel at producing convincing, high-quality outputs, but struggle to maintain multi-view and spatiotemporal consisten
arXiv:2609.12744v1 Announce Type: new Abstract: Timely monitoring of coastal water quality is critical for environmental protection, yet conventional satellite workflows rely on downlink and ground pr
arXiv:2507.01663v2 Announce Type: replace Abstract: Reinforcement learning (RL) has become a pivotal technology in the post-training phase of large language models (LLMs). Traditional task-collocated
At Anthropic, Claude now writes 80% of our code. Engineers ship 8x more code per quarter. Side effect: Tests grew 10x. CI jobs up 25x in 6 months. Here's what helped us scale: https://claude.com/blog/
arXiv:2609.12254v1 Announce Type: new Abstract: The climate literature has grown faster than review teams can read it. That gap matters most for a concept like the environmental social tipping point,
ggml-cuda: fallback to F32 on device without BF16 hardware acceleration (#28846) ggml-cuda: fallback to F32 on device without BF16 hardware acceleration: (Nvidia >= AMPERE, AMD >= RDNA3 or = CDNA) app
common : move llama_n_rs_seq to before llama_decode (#28749) This commit moves the llama_n_rs_seq function call to before the llama_decode call and returns directly if the check is true, removing the
sycl : fix oneDNN scratchpad breaking the pool free order (#28704) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47287268 macOS/iOS: macOS Apple Silicon (
ggml-cpu : disable PCH and fix CACHE_LINE_SIZE ambiguity to fix heap corruption (#28882) Disable the ggml-cpu precompiled header and remove the std::hardware_destructive_interference_size branch from
sycl: rfc: Use radix select for top_k (#28670) sycl: GPU-resident TOP_K for large k, parallelised over the device The SYCL backend refused GGML_OP_TOP_K above k = 32 and let it fall back to the CPU, a
llama.cpp : bump version to 0.4.1 (#28900) Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47376843 macOS/iOS: macOS Apple Silicon (arm64) macOS Apple Silic
ci : add ubuntu-cuda builds to release (#28186) release : add ubuntu-cuda build job (12.8/13.3, x64+arm64) Add GCC 14 for CUDA arm64 builds in CI Eplicit bash Install git for CCCL fetch Install git be
HIP: fattn-mma: use fp32 accumulation on MFMA devices (#28576) use fp32 accumulators in fattn-mma on CDNA Website: https://llama.app Attestations: https://github.com/ggml-org/llama.cpp/attestations/47
arXiv:2609.12894v1 Announce Type: new Abstract: Estimating the 3D center of mass of unknown objects is challenging when grasping is infeasible, geometry is irregular, or mass distribution is uneven. W
arXiv:2609.12896v1 Announce Type: new Abstract: LLM-based agents rely on heterogeneous interaction capabilities to accomplish complex tasks. Existing approaches often distribute these capabilities acr
arXiv:2604.05793v2 Announce Type: replace-cross Abstract: In LLM agent pipelines, prompt privacy risk propagates beyond a single model call: raw user content enters retrieval queries, memory writes, t
arXiv:2609.12303v1 Announce Type: new Abstract: Small models are made more capable through distillation from a larger one that shares their tokenization scheme. However, do distilled byte and token mo
arXiv:2609.12454v1 Announce Type: new Abstract: Vision-Language Models such as CLIP enable effective few-shot medical anomaly detection (AD) via strong image-text semantic alignment. However, their gl
arXiv:2609.12162v1 Announce Type: cross Abstract: Draft-verify-revise is a common LLM orchestration pattern for scaling inference-time compute. One LLM drafts, a second critiques the draft and provide
arXiv:2609.12365v1 Announce Type: new Abstract: In the VTaC benchmark 71% of ventricular-tachycardia alarms are false, but silencing a real one can delay recognition of a dangerous arrhythmia. We refr
arXiv:2609.12509v1 Announce Type: new Abstract: Evaluation of vision-language models (VLMs) for multimodal mathematical reasoning remains limited for low-resource languages and for geometry problems t
Claude Mods are landing now. Someone already built a Tetris-in-Claude mod 🤯 See issue for the latest community update, technical details, and more cool demos https://github.com/anthropics/claude-code/
arXiv:2609.12826v1 Announce Type: new Abstract: In order to design conservation and restoration strategies to counter the global decline of coral reefs, ecological monitoring of reefs needs to be scal
arXiv:2609.12620v1 Announce Type: new Abstract: The increasing adoption of machine learning in network and distributed security systems has created an urgent need for mechanisms that can selectively a
arXiv:2609.12758v1 Announce Type: new Abstract: Recovering unmanned aerial vehicles (UAVs) in maritime environments is challenging due to wind turbulence and ship-deck motion, making it a valuable tes
Dan Selsam is a current OpenAI capabilities researcher. (since 2022) He was my boss for a while. He doesn't have a twitter account but has made this public statement of his views on AI risk and sent i
arXiv:2604.08335v2 Announce Type: replace Abstract: We present a feedforward graph architecture in which heterogeneous frozen large language models serve as computational nodes, communicating through
Note - This is translated from the actual blog link right at the bottom. A few days ago, DeepSeek v4.1 was released. It raised the ability of small models to a new level. AI is improving much faster t