Knowledge catalogue
arXiv:2610.12464v1 Announce Type: new Abstract: World models offer a promising alternative to physics-based simulators, yet remain far from practical deployment. We ask how far scaling ego-centric hum
arXiv:2610.11188v1 Announce Type: new Abstract: Persistent memory can improve personalization in LLM agents but can also induce sycophancy and cross-domain leakage. We distinguish two governance decis
arXiv:2610.10971v1 Announce Type: cross Abstract: Large language models are increasingly used in legal research and drafting, but they can still produce claims that sound convincing without being supp
arXiv:2610.11948v1 Announce Type: new Abstract: Reliable multimodal interaction depends on selective use of conversational history: an earlier question may remain relevant while its previous answer is
arXiv:2610.11123v1 Announce Type: new Abstract: Most human-agent interaction today remains text-based. Natural language can impose cognitive overload, ambiguity, information chaos, and slow input for
arXiv:2610.11620v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) enables large language models (LLMs) to adapt to specialized tasks, but often at the cost of degrading general ca
arXiv:2610.12367v1 Announce Type: new Abstract: Skills, reusable procedural guidance added at inference, can substantially improve LLM downstream performance (Li et al., 2026). Prior work retrieves sk
arXiv:2610.11008v1 Announce Type: cross Abstract: Language-model agents favor their own group because they have watched their members favor each other. The group label alone does little once the decis
arXiv:2610.11247v1 Announce Type: cross Abstract: On-policy distillation (OPD) enables effective capability transfer between language models, yet the mechanisms underlying its failures are not fully u
arXiv:2610.11561v1 Announce Type: new Abstract: LLM-based agents now interact with their environments continuously, shaped by such organizational channels as user instructions, peer messages, and long
arXiv:2610.10622v1 Announce Type: cross Abstract: Large language models can now write complete, interactive 3D worlds as code, but grading those worlds automatically is unreliable. Existing judges tak
arXiv:2610.11184v1 Announce Type: new Abstract: Advances in image generation have made visual authenticity increasingly difficult to assess. Although image forensics now examines both generation artif
arXiv:2610.12417v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) struggle with spatial, embodied, physical, and temporal reasoning. We hypothesize that these failures reflect
1/ My heart is heavy. I made a number of mistakes in my life, and not asking earlier for an immediate slowdown is one of them. If OpenAI starts making similar breakthroughs in biology, we risk somethi
Preamble and disclaimer, Sample size: 8, at any size of form this research is just screwing around being writing it down. This was just a little,(well... big), curiosity test I wanted to run to see wh
Post title is slightly misleading, I don't think you can get these for $350 each anymore but they're still pretty cheap all things considered. They're Radeon Pro V620's which are older RDNA2 enterpris
arXiv:2610.09529v1 Announce Type: new Abstract: There are more than 2,000 listed companies on the UK's London Stock Exchange, divided into 11 sectors who are required to communicate their financial re
arXiv:2610.09835v1 Announce Type: new Abstract: Continual pre-training and fine-tuning in Large Language Models (LLMs) inevitably induce catastrophic forgetting, typically mitigated by replay using of
arXiv:2610.10014v1 Announce Type: new Abstract: Can a biological wiring diagram serve as a useful computational substrate beyond the behaviors for which it evolved? We use the publicly released MaleCN
arXiv:2610.09677v1 Announce Type: new Abstract: Self-supervised anomaly detection is a promising paradigm for medical ultrasound, as normal images are often easier to obtain than exhaustive annotation
arXiv:2603.06655v2 Announce Type: replace Abstract: We introduce FCBNet, an efficient model designed for camouflaged weed detection. The architecture is based on a fully frozen ConvNeXt backbone, the
arXiv:2602.02639v2 Announce Type: replace-cross Abstract: LLM self-explanations are often presented as a promising tool for AI oversight, yet their faithfulness to the model's true reasoning process i
arXiv:2610.10116v1 Announce Type: new Abstract: Semantic segmentation networks operate on a fixed set of classes and therefore fail when out-of-distribution (OOD) objects appear during deployment, a c
arXiv:2610.10174v1 Announce Type: new Abstract: Bayesian optimization often involves multiple objectives, constraints, and fidelity levels. We address the challenge of jointly selecting where and at w
arXiv:2610.10085v1 Announce Type: new Abstract: Post-training tensor-network compression replaces Transformer linear layers with Tensor Train (TT) or Tree Tensor Network (TTN) operators, but standard
arXiv:2610.09302v1 Announce Type: new Abstract: Safe navigation in dynamic environments requires robots to plan under obstacle predictions whose errors are uncertain, non-stationary, and can induce ra
arXiv:2610.09505v1 Announce Type: cross Abstract: We develop a bias-aware digital-twin calibration and control framework for multiscale bioprocess models within a biological systems-of-systems (Bio-So
arXiv:2610.10047v1 Announce Type: new Abstract: Product-centric advertisement video generation aims to create promotional videos that preserve fine-grained product identity while presenting selling po
arXiv:2603.29217v3 Announce Type: replace-cross Abstract: Phoneme-based ASR factorizes recognition into speech-to-phoneme (S2P) and phoneme-to-grapheme (P2G), enabling cross-lingual acoustic sharing w
arXiv:2610.09240v1 Announce Type: cross Abstract: Modern web agents built on large vision-language models process webpages, select relevant UI elements, and translate model outputs into browser action
Aisha Malik / TechCrunch: AI hardware startup Natura unveils Interface, a 99 smart ring that connects to AI agents and apps, including Claude, ChatGPT, Muse, Grok Bot, and Instinct — Meet Interface, a
arXiv:2610.10421v1 Announce Type: new Abstract: Goal-oriented Vision-and-Language Navigation (VLN) requires agents to locate and reach targets described in natural language without prescribed routes.
arXiv:2610.09003v1 Announce Type: new Abstract: Autoregressive Large Language Models (LLMs) frequently struggle with deterministic multi-step algorithmic tasks such as multi-digit multiplication and l
arXiv:2610.09661v1 Announce Type: new Abstract: Automatic Short Answer Scoring (ASAS) is central to NLP for Education. However, openly available benchmarks remain scarce, and existing datasets largely
arXiv:2610.09525v1 Announce Type: new Abstract: We introduce a calibration-first framework that produces supervision scores without access to ground-truth labels or a shared annotation space. Our fram
arXiv:2610.09459v1 Announce Type: new Abstract: This paper addresses the prediction of adjacency between pairs of 2D fragments based on their contours. We improved the two-stage architecture proposed
an open model just beat Jev outright on clinical decisions 🔥 pplx-decider v1.1 got 643 of 669 right vs 628 for Jev, at 42% less per decision and about the same speed. and you can download the weights
Another great paper from Salesforce AI Research. The finding is that a 31B open Gemma-4 web agent scores 74.6% on the 9-app WebArena Infinity set, above Gemini 3 Flash with browser use at 70.1%. They
Anthropic is making changes to its usage policy for the first time in over a year to reflect new and high-risk cases of misuse - including election interference, weapons development, surveillance, and
Anthropic's offering to help open-source projects track down security vulnerabilities with a new service called OSS Scanner. It says open-source projects that opt-in will get 'thorough, periodic secur
Anthropic: Anthropic launches OSS Scanner, a free opt-in vulnerability scanner for critical open-source projects; its AI-generated reports are sent without human review — We're launching OSS Scanner,
Sam Sabin / Axios: Anthropic launches the Critical Infrastructure Defense Program to provide AI models, threat research, and on-site support, starting with CrowdStrike and others — Anthropic is launch
Hayden Field / The Verge: Anthropic updates its usage policy to ban “sustained and needless abusive or cruel behavior” toward Claude; ending chats is “the primary enforcement mechanism” — The usage po
arXiv:2505.19912v3 Announce Type: replace Abstract: We present Adjacent Possible Exploration (APE), a selective fine-tuning method for adapting large language models that systematically explores param
arXiv:2610.09396v1 Announce Type: new Abstract: As text-to-SQL systems move beyond demonstrations toward real-world deployment, ambiguity in user questions becomes a primary source of errors. Such amb
arXiv:2610.09446v1 Announce Type: new Abstract: Large language models (LLMs) should abstain from scientific multiple-choice questions when no option is valid, but frequent abstention alone does not de
arXiv:2610.09122v1 Announce Type: new Abstract: Parameter-efficient fine-tuning (PEFT) offers many parameterizations, yet their methodological and functional differences remain unclear. We compare six
arXiv:2610.09096v1 Announce Type: new Abstract: While established literature underscores the pivotal role of preprocessing in forecasting accuracy, this stage remains largely overlooked in current res
Rachel Metz / Bloomberg: Arena, which develops the popular AI model leaderboard, raised 200M at a 3.1B valuation, up from 1.7B in January, and launches an Alignment Index — Arena Intelligence Inc., th
arXiv:2610.10181v1 Announce Type: new Abstract: Robots operating in dynamic environments require reliable detection of how their surroundings change over time. Existing learning-based methods largely
As a homicide detective, I can say with all of my being that there is no lesson learned in seeing someone die. But there is a price. And that price is your peace. Your decency. And the soul of our soc
As easy as asking After @elonmusk tweeted my guide to connecting Claude and ChatGPT to Grok @Bot, people had 5 questions. 1. Do I need an API key? Nah. Just log into Claude or ChatGPT, like you do in
arXiv:2610.10349v1 Announce Type: new Abstract: Instruction-tuned models are deployed into environments where domains are heterogeneous and evolve, yet adding new domains or data typically requires co
arXiv:2610.08825v1 Announce Type: new Abstract: Autonomous driving has made remarkable progress, with recent AI advances enabling commercial deployments that are reshaping urban mobility. Yet the fiel
llama : add a GPU cache for MoE experts kept in host memory (#29887) llama : add a GPU cache for MoE experts kept in host memory Assisted-by: Claude use llama_moe_cache_ptr Website: https://llama.app
mtmd: add cohere2 vision support (#30062) cohere2 vision model address comments remove redundant mapping follow existing patterns fused linear_1 Website: https://llama.app Attestations: https://github
cuda: FWHT kernels for block widths above 512 (#29100) The CUDA FWHT covers widths 64 to 512. It runs one row per warp and keeps N/32 values per lane, so wider blocks need more registers per lane than
model : add LiquidAI/d1-3B decision model (#30110) model : add LiquidAI/d1-3b decision model mtmd : read LFM2 image resize algo from GGUF Assisted-by: Claude Opus 5.5 common : rename decision type d1
chat : name tool and argument parser rules by index (#30088) bugfix: infinite recursion caused by a tool named 'call'(#29967) chat : use index for schema and argument rules tests : remove tests tests
chat: fix jinja parser for TranslateGemma (#30096) chat: fix jinja parser for translategemma log if missing soruce_lang_code or target_lang_code Website: https://llama.app Attestations: https://github