Knowledge catalogue
arXiv:2609.01861v1 Announce Type: new Abstract: The performance of an LLM agent depends on the scaffold around a frozen model. A common way to improve that scaffold is to use a coding agent as an opti
arXiv:2609.02735v1 Announce Type: new Abstract: Per-patient adapters are the preferred production architecture for dysarthric automatic speech recognition (ASR), yet parameter-efficient fine-tuning (P
Two weeks, one rule, and hundreds of entries from nearly 50 countries. Here's who took the four titles, and a look at everyone who made the final ten! Entries opened August 20 and closed September 1.
arXiv:2609.02730v1 Announce Type: new Abstract: Production recommender systems shape what billions of people see, and sustaining their performance requires continual optimization: as content, user beh
arXiv:2609.01787v1 Announce Type: new Abstract: Vision Transformers (ViT) excel in semantic understanding but fail to discriminate between object instances (e.g., identical embeddings for two dogs), l
arXiv:2609.01794v1 Announce Type: new Abstract: How do learners avoid overgeneralizations such as Tom laughed me without explicit negative evidence? Constructionists have posited two proposals that de
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:2609.02771v1 Announce Type: cross Abstract: Training data attribution (TDA) aims to identify training examples that shape model behavior, but its intervention value depends on both which example
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:2609.02653v1 Announce Type: new Abstract: Humans can perform complex manipulations given a simple intent through an overall instruction, while continuously adapting to evolving visual observatio
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
arXiv:2609.02289v1 Announce Type: new Abstract: Detectors trained on closed-set annotations can miss rare moving objects outside the training taxonomy. Automotive radar provides category-independent D
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.
Impressive tool to explore frontier AI capabilities. Martian's AI Frontier lets you compare 44 LLMs by measured cost, quality, and reliability, then see how routing and repeated sampling change the fr
arXiv:2609.02747v1 Announce Type: new Abstract: Achieving truly immersive large-scale scene digitization necessitates consistent and visually pleasing rendering across all possible viewing perspective
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:2609.01685v1 Announce Type: new Abstract: With the development of artificial intelligence (AI), the landscape of meta-ethics, which has largely centred on human ethics, faces pressures that may
This is mostly for setting up for expectation, since personally without LLM i could take 3 days (15 hours of active programming) to debug or implement a feature, but with Qwen 27B (even before Qwen 3.
arXiv:2609.02149v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly evolving from conversational assistants into agents capable of operating external digital environments.
Maxwell Zeff / Wired: OpenAI calls GPT-6 Astra the “world's best computer use model”; in tests, it booked DMV appointments and searched job listings faster than the average person — OpenAI leaders thi
arXiv:2609.02216v1 Announce Type: new Abstract: Inductive knowledge graph completion (IKGC) aims to predict missing links involving entities unseen during training, requiring models to learn transfera
arXiv:2609.01623v1 Announce Type: cross Abstract: Autonomous and intelligent transportation systems operate in complex urban environments where safety depends on interactions among vehicle behavior, e
ik_llama.cpp merged qwen4exp MTP support yesterday (PR #2369, mine, reviewed and tested by four other people on their own hardware). It's on main now, no fork or patch needed. Posting since the last c
Disclaimer: I'm the builder. --- Over the past 2 yrs, I was working on a SaaS ML project & got very interested in ML/DL/AI. As everybody else, there were some normal paths I took to build a solid unde
arXiv:2609.02623v1 Announce Type: cross Abstract: Voice actors often re-read the same script while modifying their delivery in response to performance directions. We study this setting as direction-fo
arXiv:2609.02217v1 Announce Type: new Abstract: LLM agents increasingly self-improve by writing and reusing textual skills, kept either as one global document or as a flat pool of per-task entries, th
arXiv:2609.01936v1 Announce Type: cross Abstract: A language model's prediction of its next token develops across layers, and lens methods track this process by decoding intermediate hidden states int
arXiv:2609.01737v1 Announce Type: new Abstract: Mobile payment applications in Nepal are graphically mediated and largely inaccessible to visually impaired users. This paper presents SpeakPay, a voice
arXiv:2609.02341v1 Announce Type: new Abstract: Vision-Language-Action models (VLAs) have shown strong potential in autonomous driving by leveraging multimodal pretraining for instruction following, v
What a super interesting paper this one is. They propose an architecture for agents that outlive their model, harness and host. Today we describe an agent by whatever model and harness it happens to r
zai earnings transcript was a really good read, a list of interesting points (mostly verbatim from the transcript): * Chat → Coding → Agent → Cowork → Autonomous AI * What truly matters is who can con
arXiv:2609.00769v1 Announce Type: new Abstract: This letter presents a compact two-degree-of-freedom (DoF) robotic finger with a flexion-selective passive continuously variable transmission (CVT) to a
arXiv:2609.00403v1 Announce Type: new Abstract: This paper presents a multi-branch fusion framework for detecting and characterising the propagation of health misinformation in online social networks
A simple but profound and critical point that everyone talking about AI should strive to understand: @deathrater03 @GaryMarcus Neurosymbolic means combining highly capable but unreliable ML ('neuro')
arXiv:2609.01289v1 Announce Type: new Abstract: Hyperspectral unmixing is a key task in remote sensing that aims to decompose mixed pixels in hyperspectral images into their constituent material signa
arXiv:2609.00090v1 Announce Type: cross Abstract: Feature importance Methods (FIMs) are widely used in Explainable AI to interpret model predictions, yet attribution scores alone often provide limited
arXiv:2609.01100v1 Announce Type: new Abstract: In current Mixture-of-Experts architectures, routing is performed based on representations dominated by structure shared across all tokens, limiting exp
arXiv:2609.00874v1 Announce Type: new Abstract: As agentic systems become compound systems, increasingly important decisions move above task execution itself: when should a higher-level controller pre
arXiv:2602.03708v3 Announce Type: replace Abstract: Large Language Models (LLMs) achieve strong performance across many tasks but suffer from high inference latency due to autoregressive decoding. The
arXiv:2609.01195v1 Announce Type: new Abstract: Entity matching (EM) requires fine-grained contextual understanding and domain knowledge. Recent work shows that large language models (LLMs) can serve
arXiv:2609.01575v1 Announce Type: new Abstract: Extracting structured fields from hundreds of millions of documents annually remains costly in regulated industries: bespoke OCR cascades cover only a f
arXiv:2609.00759v1 Announce Type: new Abstract: Large language models (LLMs) increasingly handle in-context learning (ICL) tasks where a long, novel context defines the rules, knowledge, and output sc
arXiv:2609.01200v1 Announce Type: new Abstract: When the visual encoder and the language decoder of a vision-language model (VLM) run on different compute nodes, the intermediate visual-token embeddin
arXiv:2609.00576v1 Announce Type: new Abstract: Item-sensitivity, defined as whether a model's choice depends on the specific input rather than on its own output prior, is widely reported as evidence
arXiv:2609.00621v1 Announce Type: new Abstract: Prompt optimization can improve multi-agent LLM systems, but the prompts being optimized often serve two entangled roles: generating task-relevant conte
arXiv:2609.00709v1 Announce Type: cross Abstract: Large Vision-Language Models produce fluent image descriptions but offer limited semantic control: users cannot reliably specify whether captions shou
arXiv:2609.00441v1 Announce Type: new Abstract: Effective manager-employee communication is critical for retaining high performers and developing underperformers, yet training managers in these skills
arXiv:2609.00683v1 Announce Type: new Abstract: Creative generation tasks, such as narrative writing and scientific ideation, demand both high-quality outputs and distinct responses across independent
arXiv:2609.00833v1 Announce Type: new Abstract: Reinforcement learning (RL) for search agents typically relies on outcome rewards. However, it often fails to achieve effective credit assignment, due t
arXiv:2609.00100v1 Announce Type: new Abstract: Psychometric questionnaires contain rich item-level information, yet it remains unclear whether different representation learning objectives recover the
arXiv:2609.00206v1 Announce Type: cross Abstract: Despite their growing use in video moderation, multimodal large language models (MLLMs) exhibit a compositional safety blind spot: videos composed of
Don't count out Gemini just yet. Feels like a new era of model releases. Models are so powerful that they now come with cyber variants. Love the pricing on Gemini 3.8 Flash. Performance not bad. Gemin
arXiv:2609.00662v1 Announce Type: new Abstract: A multi-model language service must route each request while preserving workload-level budgets for compute, latency, memory, or monetary cost. Two featu
arXiv:2609.00479v1 Announce Type: new Abstract: For emerging scientific research domains, local Small Language Models (SLMs) are becoming more attractive, as they offer stronger privacy control and mo
arXiv:2609.00023v1 Announce Type: cross Abstract: In this paper, we introduce ES-AHD, a novel framework that fundamentally integrates Evolution Strategy (ES) into Large Language Model (LLM)-driven Aut
Fable 5.1 didn't come with document OCR benchmarks, so we benchmarked it on ParseBench: a comprehensive parsing benchmark that's comprised of 2k+ real-world documents across finance, legal, insurance,
arXiv:2609.00961v1 Announce Type: new Abstract: Conversational agents like chatbots and voice assistants are trained to understand and respond to user intents. On encountering an utterance with an int
arXiv:2609.01198v1 Announce Type: new Abstract: Repeated banking interactions require assistants to maintain complete, current, and traceable customer records as life changes emerge incidentally in ro
arXiv:2609.00788v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) have extended the capability of large language models (LLMs) to process more contextual multimodal information,
arXiv:2609.00051v1 Announce Type: cross Abstract: Despite extensive alignment efforts, Large Language Models (LLMs) remain vulnerable to generating unsafe content under adversarial prompting, yet the