Knowledge catalogue
Ina Fried / Axios: OpenAI says it is cutting the price of GPT-5.6 Luna by ~80% and the price of GPT-5.6 Terra by 20% after improving the efficiency of the systems that serve them — OpenAI said Thursda
Our partners at @depthfirstlabs just released dfs-large1, a specialized model built for finding and validating real vulnerabilities in large enterprise codebases. We helped them to scale the training
Greetings Community! 👋 I hope everyone is doing well! I'm Tauhid — Senior EEE student from a Bangladeshi University Today I'd like to share an open-source project I’ve been developing called P.A.I. (P
arXiv:2607.27073v1 Announce Type: new Abstract: We study online convex optimization (OCO) in non-stationary environments under heavy-tailed noise, where the stochastic gradient oracle admits only a fi
arXiv:2602.21987v3 Announce Type: replace Abstract: Low-dose CT images are essential for reducing radiation exposure in cancer screening, pediatric imaging, and longitudinal monitoring protocols, but
arXiv:2603.15384v2 Announce Type: replace-cross Abstract: We improve and extend persistence spheres, introduced in~ite{pegoraro2025persistence}. Persistence spheres map an integrable measure mu on the
arXiv:2607.26751v1 Announce Type: new Abstract: State-of-the-art intracortical brain-to-text systems pair a neural-sequence phone decoder with an external language model. Two design axes remain undere
Voice assistant and conversational AI agent developer PolyAI Ltd. today announced the release of Dialog-RSN-1, a voice dialog artificial intelligence model capable of directly perceiving and respondin
arXiv:2607.26191v1 Announce Type: cross Abstract: Evaluation methodologies for language models increasingly combine multiple signals, from automated metrics and LLM-as-judge ratings to human assessmen
arXiv:2607.26358v1 Announce Type: new Abstract: Reinforcement learning (RL) fine-tuning is widely used in language model training to improve model performance on a target task while limiting drift fro
arXiv:2607.26710v1 Announce Type: new Abstract: The rapid growth of AI workloads is turning data centers into large-scale, volatile, yet spatiotemporally flexible grid loads, creating an urgent need f
arXiv:2607.26947v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) rely on a projector to align visual representations with the language embedding space, making it central to cro
arXiv:2606.14636v2 Announce Type: replace Abstract: Control-function instrumental-variable estimators pass an estimated first-stage residual to an outcome model. The residual must retain the latent co
arXiv:2607.26541v1 Announce Type: cross Abstract: Audio-capable foundation models enable end-to-end spoken interaction, but they also introduce safety risks beyond transcript content. It remains uncle
Quick reminder of what's ok vs not ok with harnesses used for playing ARC-AGI-3: 1. Not okay: harnesses that were custom-made to solve the benchmark or that contain knowledge about the benchmark forma
arXiv:2607.26196v1 Announce Type: new Abstract: Self-supervised pretraining is central to 3D medical image analysis, where unlabeled CT volumes are abundant but expert annotations are scarce. Yet exis
arXiv:2607.26339v1 Announce Type: new Abstract: Retrieval-Augmented Generation (RAG) systems ground large language models (LLMs) in external corpora, but this reliance exposes them to corpus poisoning
arXiv:2607.26862v1 Announce Type: new Abstract: Group Relative Policy Optimization (GRPO) has become a standard reinforcement learning method for post-training language models. Recent work shows that
arXiv:2607.26337v1 Announce Type: new Abstract: Suture-needle pickup is necessary for autonomous suturing, as a needle can be unexpectedly dropped or strategically released to adjust the grasping conf
arXiv:2607.26643v1 Announce Type: cross Abstract: Enabling large language model (LLM) agents to accumulate and reuse experience from past interactions remains a central challenge in real-world applica
arXiv:2607.26802v1 Announce Type: new Abstract: This paper presents a radial basis function network (RBFN)-informed motion planning framework for safe and efficient urban autonomous driving. The propo
arXiv:2607.26807v1 Announce Type: new Abstract: While MoE augments VLA via expert specialization, router suffers from ineffective expert routing owing to the kinematic heterogeneity of actions across
arXiv:2607.26929v1 Announce Type: new Abstract: The same diagnostic result can support or challenge one causal claim yet fail to address another when the claims concern different populations, outcomes
arXiv:2607.27084v1 Announce Type: new Abstract: Scientific images are the core elements of presenting experimental conclusions, elaborating system architecture, and supporting comparative arguments in
arXiv:2607.26791v1 Announce Type: cross Abstract: Large Language Model (LLM) agents are increasingly adopted in real-world security operations with access to host artifacts and command-line interfaces
arXiv:2607.26326v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) achieve strong performance by integrating visual inputs with the rich priors of pretrained language models. How
arXiv:2607.26511v1 Announce Type: new Abstract: UAV Anti-UAV tracking is an emerging low-altitude security task for localizing an adversarial UAV using the onboard camera of a moving observer UAV. It
arXiv:2607.26873v1 Announce Type: new Abstract: Test-time reinforcement learning (TTRL) enables language models to self-evolve at inference time without labeled feedback. Existing methods rely on answ
arXiv:2607.27056v1 Announce Type: cross Abstract: Personalized agents are increasingly applied to assist users across a wide range of tasks. Effective personalized assistance requires not only retriev
arXiv:2607.26173v1 Announce Type: new Abstract: Alignment training, model organisms, and toy models are usually treated as separate research areas. But projects in all three frequently use supervised
arXiv:2607.26577v1 Announce Type: new Abstract: Adaptive conformal inference (ACI) of Gibbs and Cand{es and its variants are the standard approach to online conformal prediction under distribution shi
arXiv:2607.26595v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) has emerged as an effective representation for novel view synthesis and 3D scene reconstruction, creating an increasing dem
arXiv:2602.11219v2 Announce Type: replace Abstract: Predictive uncertainty is commonly decomposed into epistemic and aleatoric components, but standard decompositions often produce strongly correlated
sure we lose money on every inference but we make it up in volume We are committed to pushing the model frontier across cost efficiency, capability, and speed. Starting today, we are reducing prices f
arXiv:2607.26355v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly embedded in everyday life and widely used for information seeking, raising concerns about their potential
arXiv:2607.26924v1 Announce Type: new Abstract: Recent work on LeWorldModel (LeWM) has shown that the Sketched Isotropic Gaussian Regularizer (SIGReg) enables stable end-to-end world-model learning fr
arXiv:2607.26523v1 Announce Type: new Abstract: We introduce CMP (Cognitive Memory Primitive), a continual-learning architecture that repre?sents inputs as sparse relational codes, stores them in a tw
arXiv:2503.10647v2 Announce Type: replace Abstract: This study evaluated the diagnostic reliability of two Large Language Models (LLMs), Google Gemini 2.0 Flash and OpenAI ChatGPT-4o, across three dim
Thinking Machines just released Inkling-Small: 276B total, 12B active. A faster Inkling that matches or beats its 975B big brother in many benchmarks. To test its speed, we plugged it into HF's speech
This is absolutely wild... Anthropic reviewed their logs and found out that their own supposedly-sandboxed cyber evals had hacked three separate companies back in April without them noticing! In a rev
arXiv:2607.26838v1 Announce Type: new Abstract: In this paper we show that the generalization error of AdaBoost is Thetaig(frac{dln(ngamma^{2}/d)}{ngamma^2}+frac{ln(1/elta)}{n}ig), where gamma is the
arXiv:2603.09971v2 Announce Type: replace Abstract: We present TiPToP, a modular manipulation system that integrates pretrained foundation models with a GPU-accelerated Task and Motion Planner to solv
arXiv:2607.26121v1 Announce Type: new Abstract: Embodied intelligence integrates learned perception and decision making with real-time computation, control, and physical interaction. Because failures
arXiv:2607.26849v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed in high-stakes domains, adversaries may poison training data to implant backdoors: hidden triggers that c
arXiv:2607.26536v1 Announce Type: new Abstract: High-pressure prompts can push vision-language models (VLMs) into unsupported commitments, such as reading illegible text, reporting indeterminate times
arXiv:2510.00192v3 Announce Type: replace Abstract: Low-rank adaptation (LoRA) has become a widely used paradigm for parameter-efficient fine-tuning of large language models, yet its representational
arXiv:2603.17019v2 Announce Type: replace Abstract: A central question in the debate over large language models is whether transformers can learn rules they have never seen, or whether they can only i
arXiv:2607.27027v1 Announce Type: new Abstract: Gradient-boosted trees dominate tabular machine learning, yet canonical correlation analysis has always relied on linear or neural encoders. We propose
arXiv:2607.26977v1 Announce Type: new Abstract: Travel planning is a demanding stress test for tool-using LLM agents: a usable itinerary is a single artifact that must be right along many axes at once
Its a custom Swift/Metal inference engine that runs Gemma 4 26B-A4B-IT on M-series Macs with very low RAM. It uses ~2GB instead of ~14 GB. The result is reportedly 5–6 tok/s on an 8 GB M2 MacBook Air
arXiv:2607.26922v1 Announce Type: new Abstract: Multi-agent LLM pipeline systems break down the task among multiple roles for better reasoning, but are benchmarked mainly with large-scale commercial m
DigitalOcean launched Kimi K3 on day 0. It’s already one of the most popular models on the platform and across the market: second most likes on Hugging Face, sixth most traffic on OpenCode. Getting a
arXiv:2607.26608v1 Announce Type: new Abstract: Training-free fusion of heterogeneous multimodal large language models (MLLMs) provides a direct route for cross-scale capability transfer, yet improvem
arXiv:2606.18426v2 Announce Type: replace Abstract: We introduce VEGA, an approach for training navigation VisionLanguage-Action (VLA) models from unlabeled egocentric navigation videos. Internet-scal
arXiv:2607.27069v1 Announce Type: new Abstract: Closed yes/no spatial benchmarks can reward a correct answer even when the image adds little support beyond no-image contexts. Under a fixed forced-choi
We are committed to pushing the model frontier across cost efficiency, capability, and speed. Starting today, we are reducing prices for GPT-5.6 Luna by 80% and GPT-5.6 Terra by 20% , and offering a f
arXiv:2607.27017v1 Announce Type: new Abstract: A central premise of latent world models is that predicting the future forces a representation to internalize the physics of its environment. Which phys
Is Qwen 3.6 27b still the go' ol' reliable at this point? I know 35b is faster but it just doesn't give as good results. Is it possible to run deepseek v4 flash on a single spark at decent tk/s withou
I've tried grok and Claude's deep research mode and I was amazed with the speed considering the amount of sources analysed. Is there anything as fast that can run locally? My guess would be that to ru
arXiv:2607.26159v1 Announce Type: cross Abstract: An AI benchmark result rarely reaches a consequential claim in one step. Evaluators generalize it to further cases, interpret it as evidence of capabi