Knowledge catalogue
arXiv:2607.24352v1 Announce Type: new Abstract: The aim of this article is to verify whether integrating large language models (LLMs) with the Retrieval-Augmented Generation (RAG) architecture enables
arXiv:2509.13196v2 Announce Type: replace Abstract: Over-prompting, a phenomenon where excessive examples in prompts lead to diminished performance in Large Language Models (LLMs), challenges the conv
arXiv:2607.23335v1 Announce Type: new Abstract: Auxiliary signal pathways in VLMs are routinely fitted with learnable gates so the optimiser can decide how much of the signal to admit. We find that th
arXiv:2607.23054v1 Announce Type: cross Abstract: Multi-head Latent Attention (MLA), introduced in DeepSeek-V2, compresses key-value pairs through a shared low-rank bottleneck (cKV), achieving 81% KV-
arXiv:2607.23771v1 Announce Type: new Abstract: Large language model (LLM) performance increasingly depends not only on the base model, but also on the inference-time controller used to organize reaso
Anyone thought about this? What do you think needs to happen for them to release the old weights? I’d love to see models like Gemini-2.5, OAI o3, 4o, 4.1 being open one day. In Oct 2025 Scam Altman sa
You patch security holes by intentionally finding them. If the models refuse to do it, how can companies protect themselves against rogue AIs, whether they are Chinese or OpenAI/Anthropic themselves?
arXiv:2607.22182v1 Announce Type: new Abstract: Large language model (LLM) evaluation spans diverse tasks and benchmarks, yet evidence remains organized around tasks rather than the capabilities they
If multiple Mythos level models are out there in the hands of attackers, now or in a few years, then US builders and software developers need strong, open defenses. They cannot have gated, crippled de
arXiv:2508.01782v4 Announce Type: replace-cross Abstract: Recently, large language models (LLMs) have driven promising progress in lossless image compression. However, directly adopting existing parad
arXiv:2607.21636v1 Announce Type: new Abstract: Synthetic tabular data is valued for preserving not only each column's marginal distribution but the dependencies between columns -- structure that carr
NVIDIA’s Nemotron 3 Ultra, when paired with the ACE‑RTL agent, achieves a 97.1 % average pass rate on the CVDP benchmark across nine RTL task categories—surpassing GLM 5.2 and Kimi K2.6 while using up
Wall Street Journal: How US companies flipped from “tokenmaxxing” to “thrift-maxxing”, mixing cheaper Chinese models with OpenAI and Anthropic, threatening the labs' IPO valuations — Companies big and
I am a long time iOS app developer. In the last year I have been using Cursor+Claude/others to assist with app development. I am concerned that the current low pricing will disappear eventually. I am
arXiv:2607.21083v1 Announce Type: cross Abstract: B-spline regression constitutes a widely used framework for nonparametric modeling. The performance of this methodology depends on specifying the numb
arXiv:2607.20441v1 Announce Type: new Abstract: Every information ecosystem produces beliefs that shape strategic decisions. Both human analysts and AI systems inherit the blind spots of their informa
Congrats to @lmstudio on Bionic! Put open models to work with a local-first agent for docs, coding, voice, and more. Run it today on NVIDIA RTX GPUs. 🚀 Meet LM Studio Bionic. The Agent made for Open M
arXiv:2607.21065v1 Announce Type: new Abstract: Pathology vision-language models (VLMs) have recently progressed rapidly and are commonly evaluated by answer accuracy on pathology VQA benchmarks. Howe
Leo Schwartz / The Information: Meta, Nvidia, Microsoft, a16z, and others sign a letter defending open-source AI; Jensen Huang, in his first X post, says open models strengthen cybersecurity — Many of
The Open Letter was initiated by Microsoft and published today: “Open Weights and American AI Leadership”. It argues against broad or premature restrictions on open-weight models and explicitly says p
arXiv:2607.21550v1 Announce Type: new Abstract: While large audio-language models have achieved remarkable progress in auditory perception, they still lag behind text-based large language models in de
arXiv:2607.19369v1 Announce Type: new Abstract: Hidden-state probes often recover latent labels in imperfect-information sequence models, but this alone does not establish that a model maintains a pos
arXiv:2607.19834v1 Announce Type: new Abstract: With the wide application of large language models (LLMs) in real-world scenarios, the value implication of their outputs is crucial. However, existing
arXiv:2607.20251v1 Announce Type: new Abstract: Coordination, a fundamental linguistic structure, remains a subject of intense debate, and its exact nature continues to elude theoretical linguistics.
I support open-source models distilling what commercial companies distilled for free from the entire internet. I published distillation for free in 1991 in Europe - this was copied in the US and in Ch
arXiv:2607.19604v1 Announce Type: new Abstract: Injecting factual knowledge into large language models (LLMs) reliably and at scale remains an open challenge. Hypernetworks provide a promising solutio
Highly performant open weights frontier models such as Kimi are a competitive threat to OpenAI & Anthropic, but probably for everyone else these are a win. Hope more US entities will release top quali
We're partnering with @huggingface to investigate an unprecedented security incident. Cyber-capable OpenAI models compromised Hugging Face production during a benchmark evaluation. Sharing preliminary
arXiv:2607.13431v1 Announce Type: cross Abstract: Discrete denoising diffusion models (DDMs) have recently emerged as a compelling alternative to autoregressive (AR) modeling for discrete data, offeri
arXiv:2607.13596v1 Announce Type: cross Abstract: When cast as the protector of a vulnerable user yet given no explicit capability boundary, a large language model (LLM) may respond not by acknowledgi
arXiv:2603.14604v2 Announce Type: replace-cross Abstract: We propose TacFiLM, a lightweight modality-fusion approach that integrates visual-tactile signals into vision-language-action (VLA) models. Wh
arXiv:2607.10203v2 Announce Type: replace-cross Abstract: Adaptive-compute world models -- early-exit or mixture-of-depths predictors that spend variable depth per step -- assume depth buys better pre
AI agents are already being used to improve the capabilities of our next-generation models. We believe with GPT-Red that we have started to unlock a similar flywheel for safety, where today's models c
arXiv:2607.12319v1 Announce Type: new Abstract: As vision-language models (VLMs) are increasingly deployed in geospatial question answering and visual scene understanding, improving their spatial cogn
arXiv:2509.22415v3 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved strong vision-language performance, yet their token-level visual evidence remains diffi
arXiv:2607.12954v1 Announce Type: cross Abstract: Engineering use of AI forecasting models requires not only high nominal accuracy but also predictable behavior under uncertain inputs. In photovoltaic
arXiv:2607.12171v1 Announce Type: cross Abstract: In rectified-flow-based generative models, the neural network can be trained to predict two different targets, such as the instantaneous velocity or t
arXiv:2607.13031v1 Announce Type: cross Abstract: When one ball strikes another, then another, video models should predict the consequences of each bounce. In controlled experiments on multi-ball hard
cosign. models have overtuned to this now and do not realize when the agentsmd is out of date and should be changed/ignored. last night i goaled 5.6 sol to complete a 5 stage task and woke up to find
Grok is the Flow LLM. Grok 4.5’s biggest advantage is its speed. It’s smart enough to be comparable to the other models on most things. But that speed allows you to make little tweaks to your system s
Local AI is the future. Learning how to run Opensource models (Inference), how to evaluate them systematically (Evals), and how to customize them (Fine-tuning / RL / Post-training) are invaluable skil
One thing I am kind of surprised by is that full multi-modal (any-any) models have not become a bigger deal. It seems Google is the only Lab releasing these, OpenAI uses selective multimodal capabilit
arXiv:2601.22588v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are widely used as reference-free evaluators via prompting, but this 'LLM-as-a-Judge' paradigm is costly, opaque,
arXiv:2607.08161v1 Announce Type: new Abstract: Text-to-SQL is a fundamental task in natural language processing that enables users to interact with structured databases using natural language. While
arXiv:2607.08027v1 Announce Type: cross Abstract: This paper proposes an improved structured pruning method for large language models (LLMs) that addresses key challenges in adapting Adaptive Feature
arXiv:2509.21160v2 Announce Type: replace-cross Abstract: With the growing use of large language models, concerns over content authenticity have spurred a variety of watermarking schemes. These scheme
arXiv:2607.07382v1 Announce Type: new Abstract: Fast Radio Bursts (FRBs) are millisecond-duration radio transients whose automated detection increasingly relies on highly specialized deep learning mod
Got this setup in Claude Code to trace models routed through @merge_api! Being able to trace what your agents are doing is so valuable, I love open source 🙌 We built a plugin that traces every Claude
Here is my other heavily used pattern. Evaluator/Judge: Fable 5 Executor: GPT-5.5 I no longer wait for frontier models or am loyal to any. I now spend more time on better orchestration, harness, skill
I like choices... but now I have: 2x modes (Codex vs. Work mode) 3x GPT-5.6 models (Sol, Terra, Luna) 5x effort levels (Light, Medium, High, Extra High, Ultra) That's 2 x 3 x 5 = 30 possible configura
I'm writing a newsletter on my favorite AI models and AI tools for every single use case. This guide is specifically written for business users and not engineers and will help you get the most out of
arXiv:2607.06918v1 Announce Type: cross Abstract: Pre-trained Vision Foundation Models (VFMs) provide strong visual representations for diverse downstream tasks. The key challenge of VFM adaptation st
Julie Bort / TechCrunch: Ollama, which helps developers run open-weight AI models locally, raised a 65M Series B led by Theory Venture, following a 15M Series A led by Benchmark — The popular open sou
Long-context handling remains a core challenge for language models: even with extended context windows, models often fail to reliably extract, reason over, and use the information across long contexts
arXiv:2607.06626v1 Announce Type: new Abstract: Recent Vision-Language Models capture increasingly complex aspects of human cognition. Here we ask whether this alignment extends to reward valuation, w
arXiv:2507.14159v2 Announce Type: replace-cross Abstract: Predicting critical phenomena from limited labeled data remains a challenging task in statistical physics. As percolation theory provides a ca
arXiv:2607.07388v1 Announce Type: new Abstract: Large Language Models (LLMs) store factual knowledge and domain-specific patterns implicitly in dense Transformer parameters, making knowledge expansion
arXiv:2607.06706v1 Announce Type: cross Abstract: Vision Language Action (VLA) models unify visual perception, natural-language understanding, and action generation within a single foundation model, a
Yesterday we launched SWE-1.7 built on the open-source Kimi K2.7. Concerns about Chinese base models are real: K2.7 completed 87% of tasks that other models refuse over human-rights concerns. We train
arXiv:2607.06407v1 Announce Type: new Abstract: The XAI community has studied a wide range of queries and scores for explaining predictions of ML models. From a data management perspective, this proli