Knowledge catalogue
arXiv:2609.01611v1 Announce Type: new Abstract: Frontier large language models can often recognize when they are being evaluated, a capability known as evaluation awareness. If models behave different
arXiv:2503.17039v3 Announce Type: replace-cross Abstract: Automatic text summarization relies on automatic evaluation to quickly determine the quality of summarization models via automatic metrics and
arXiv:2511.04147v2 Announce Type: replace Abstract: Safe reinforcement learning (RL) aims to optimize long-term performance while adhering to safety requirements. However, many practical applications
arXiv:2609.01865v1 Announce Type: cross Abstract: Embedding-based code retrieval is a core component of coding agents and retrieval-augmented code generation, where retrieving correct code matters mor
arXiv:2509.06272v5 Announce Type: replace-cross Abstract: Swarm-based optimization algorithms have demonstrated remarkable success in solving complex problems, yet their widespread adoption remains li
arXiv:2609.01691v1 Announce Type: new Abstract: Vision-language models (VLMs) are increasingly used to make decisions from visual inputs. We introduce FAIRLENS, a benchmark and evaluation framework fo
arXiv:2603.19539v2 Announce Type: replace-cross Abstract: We introduce an expert curated, real-world benchmark for evaluating document-grounded question-answering (QA) motivated by generic drug assess
arXiv:2609.02101v1 Announce Type: cross Abstract: Federated learning (FL) lets institutions train a shared model without exchanging data, and Low-Rank Adaptation (LoRA) makes this practical at scale b
arXiv:2609.02529v1 Announce Type: cross Abstract: Image enhancement and restoration have become standard back-end operations on short-video and social media platforms to boost UGC visual experience. Y
arXiv:2512.24016v2 Announce Type: replace Abstract: Realistic virtual try-on (VTON) concerns not only faithful rendering of garment details but also coordination of the style. Prior art typically purs
In late‑morning UTC 2026 a rare, overlapping outage hit the four largest cloud AI models—OpenAI’s ChatGPT and Codex, Anthropic’s Claude (Mythos 5.1, Fable 5.1, Opus 5, Sonnet 5), xAI’s Grok, and Googl
arXiv:2609.02804v1 Announce Type: cross Abstract: For more than 20 years, the Model-RB benchmark frb100-40 remained an open challenge; since 2014, its public record had stood at 99 of 100 variables. W
arXiv:2604.02198v2 Announce Type: replace Abstract: While Artificial Intelligence (AI) offers transformative potential for operational performance, its deployment in safety-critical domains such as av
arXiv:2609.01725v1 Announce Type: new Abstract: Audio Description (AD) provides spoken narration of visual events during dialogue gaps, making movies accessible to visually impaired audiences. The pro
arXiv:2609.02168v1 Announce Type: new Abstract: Fragmented safety evaluation undermines the governance of dangerous AI capabilities. We present a modular framework that evaluates each model through th
arXiv:2609.01878v1 Announce Type: new Abstract: Activation steering suppresses undesired behaviors in language models by adding a steering vector to the hidden state during generation. Recent conditio
arXiv:2607.09791v2 Announce Type: replace-cross Abstract: The multiplicative repetition penalty shipped across the LLM inference ecosystem (HuggingFace, vLLM, llama.cpp, and a dozen further engines) b
arXiv:2609.02683v1 Announce Type: new Abstract: Earth observation is fundamentally multi-scale; geospatial tasks span varied resolutions, and satellite imagery is organized into cascading tile pyramid
arXiv:2609.02012v1 Announce Type: new Abstract: Point-of-interest (POI) localization -- matching a user's close-up storefront photograph against large-scale geo-tagged street-view imagery -- underpins
I've been using Deepseek V4 Flash 0731 for a few weeks now and while I havent thrown it anything very hard, im quite happy with it. Using through antirez's great ds4 project. They've added support for
arXiv:2609.02349v1 Announce Type: new Abstract: Rendering accurate text remains difficult for image generation and editing models, especially when the target contains long, complex, and densely arrang
Just three weeks after its last large language model release, Google LLC today launched Gemini 3.8 Flash and Gemini 3.8 Flash Cyber. The two LLMs are based on the same technical foundation. The primar
For the ninth consecutive year, Gartner® has named Google a Leader in the Gartner Magic Quadrant™ for Strategic Cloud Platform Services, positioned furthest for Completeness of Vision. We believe this
Google is rolling out AI-powered voice assistant modes for Gmail, Docs, and Keep that allow you to manage the apps by talking to them. The real time conversational capabilities are called Gmail Live,
TimesFM-3 is the third generation of Google Research's zero-shot forecasting model, and the main change from 2.5 is that it handles multivariate inputs natively instead of being limited to a single se
GPT-6 Astra is coming to Devin. On FrontierCode 1.1, Astra performs within 0.4 points of Fable 5 at a 64% lower cost. It also sets a new SOTA on our internal testing benchmark, generating more compreh
GPT-6 Astra is state-of-the-art on FrontierMath Tier 4, ARC-AGI 3, and TerminalBench-4.0. GPT‑6 Astra is also a major advance for scientific discovery, with state-of-the-art performance on Terminal-Be
GPT-6 Astra is the most intelligent and aligned model in the world, and sets a new state of the art for computer use, browsing, software engineering, cybersecurity, science, and professional work. htt
Greg Kamradt / ARC Prize: GPT-6 Astra scores 62.7% on ARC-AGI-3 with the standard harness and 99.9% with a new provider adapter harness; Claude Opus 5 scored 30.2%, and GPT-5.6 Sol 7.8% — Summary — GP
GPT‑6 Astra GPT-6 Astra is 'rolling out today to a limited set of organizations and over the coming days will become available to all ChatGPT Plus, Pro, Business, and Enterprise users, as well as thro
arXiv:2312.06315v2 Announce Type: replace Abstract: Warning: This paper contains content that may be offensive or upsetting. There has been a significant increase in the usage of large language models
arXiv:2511.05187v2 Announce Type: replace Abstract: We study whether otherwise-idle inference resources could reduce the scarce-GPU cost of training. Our analysis uses a simulated compute ledger in wh
arXiv:2609.02876v1 Announce Type: cross Abstract: Ordinary differential equations (ODEs) underlie models in science and engineering, and many applications need derivatives of their solutions with resp
arXiv:2609.02684v1 Announce Type: new Abstract: Deploying 3D point cloud models on edge hardware such as the NVIDIA Jetson Orin Nano is severely constrained by compute and memory budgets. Existing com
arXiv:2507.21815v2 Announce Type: replace Abstract: Millions of individuals' well-being are challenged by the harms of substance use. Harm reduction as a public health strategy provides non-judgementa
arXiv:2609.01736v1 Announce Type: cross Abstract: Large language models (LLMs) augmented with external tools have demonstrated remarkable capability in solving complex real-world tasks. However, exist
arXiv:2609.01723v1 Announce Type: cross Abstract: Text-to-Speech (TTS) foundation models are increasingly fine-tuned on private datasets to synthesize highly personalized voices, introducing severe pr
arXiv:2609.01660v1 Announce Type: cross Abstract: Production deployments of large language model (LLM) agents remain unreliable on long, multi-step workflows even as benchmark success rates climb stea
arXiv:2609.02482v1 Announce Type: new Abstract: In this paper, we analyze how Large Language Models (LLMs) employ worldbuilding strategies, focusing on setting as one measurable dimension of storyworl
Chris Welch / Bloomberg: HTC rolls out its $499 Vive Eagle, which let users choose between Gemini or ChatGPT as their assistant, in North America, Europe, the UK, and Australia — HTC Corp. is rolling
Bloomberg: Humain launches humain-m3, an Arabic-language model developed with MiniMax, amid controversy among US allies over sovereign AI built with Chinese models — Saudi Arabia's artificial intellig
arXiv:2609.02772v1 Announce Type: new Abstract: Low-resource authorship style transfer (LAST) aims to rewrite text into the style of an arbitrary target author using only a few reference examples whil
If you are like me and use Google flow for NB2/NBP there is hope to finally ditch it. Let me start off by saying I’m not very impressed with any of the current local image edit or Image Reference mode
I had to look twice at this table. I know they are just numbers, but how the heck do you beat a competitor model released just a couple of days ago on some of the toughest benchmarks out there? Someth
I have been trying to squeeze TTS stack down far enough to run in a $3 chip which has 512kb of SRAM without NPU. While trying to get to that milestone i built sanoTTS which has - 11 voices, 6 language
I tested Astra early. What I would want EVERY business professional to know about the brand-new model from OpenAI: 1) Computer use and browser use are just incredible. I'm confident that pretty much a
I trust these vibe checks more than I trust most of the benchmark results GPT-6 astra seems more powerful for e2e automation and better at writing (a massively underrated gap for these models). But it
more sizes (probably still uploading): https://huggingface.co/IFM/K2-Horizon-32B-GGUF https://huggingface.co/IFM/K2-Horizon-7B-GGUF https://huggingface.co/IFM/K2-Horizon-3.7B-GGUF https://huggingface.
arXiv:2609.02422v1 Announce Type: new Abstract: Broad Learning System is an efficient randomized learning model that expands network width through feature and enhancement nodes and estimates the outpu
arXiv:2609.02396v1 Announce Type: new Abstract: Radiology reports are written primarily for clinicians, and their specialized terminology often makes them difficult for patients to interpret. As a res
I want to share a short paper just published exploring a simple but surprisingly effective optimization for sparse MoE reasoning models. The idea: Instead of retraining anything, we just tweak the rou
arXiv:2609.02745v1 Announce Type: cross Abstract: Selecting a retrieval model for a production RAG system requires reliable comparative evaluation, but obtaining relevance judgments at scale is expens
arXiv:2609.01832v1 Announce Type: cross Abstract: Patients with depression present with diverse symptom profiles, yet clinical practice routinely reduces this variation to a single severity score. Lar
It started as a fork of llama-swap, but I have been building it out for myself since then as a convenient tool for all my local AI needs, and by now it has drifted far enough to be its own thing. The
Just because someone puts the word AGI in their benchmark doesn't make it even remotely a reflection of what the general public understands by this term. As a layman, I define AGI as a virtual charact
Krea 2 Turbo — 4-Step Distillation LoRA (work in progress) A LoRA for Krea 2 Turbo that reduces the minimum usable step count from 8 to 4. ⚡ Half the steps — 8 → 4, on Turbo's own deployment sigmas. ⏱
arXiv:2609.02737v1 Announce Type: cross Abstract: Language models spend most of their attention on a small fraction of context, yet they read the entire KV cache to find the few tokens that matter. If
arXiv:2609.02207v1 Announce Type: cross Abstract: Real-world personally identifiable information (PII) redaction often operates on document images---scans, screenshots, and PDF renderings---where OCR
arXiv:2609.02473v1 Announce Type: new Abstract: Ontology rankers remain useful for rare-disease diagnosis because each candidate can be traced to matched patient phenotypes. Large language models (LLM
arXiv:2609.01928v1 Announce Type: new Abstract: Higher-order interaction components are important for signal, image, and video modeling, but explicit high-order operators often suffer from rapidly inc