Knowledge catalogue
arXiv:2608.13675v1 Announce Type: cross Abstract: Between October 2018 and July 2026 AI models progressed from simple systems like BERT to massive agents that solve complex math and write software. Th
arXiv:2608.14065v1 Announce Type: cross Abstract: Background: Software bugs remain a critical challenge in development, necessitating effective Automated Program Repair (APR) techniques. While Large L
damn deepseek moves fast on roon tweets the major ai companies should commit to a real time priced API product. ai demand varies wildly over a day/night curve and the industry is broadly extremely cap
arXiv:2608.12486v1 Announce Type: new Abstract: Large language models (LLMs) cannot retain post-deployment experience without parameter updates. We introduce DIVE, a diversity-driven framework that en
arXiv:2608.12630v1 Announce Type: cross Abstract: While large language models can generate entire novels, there is little information about the level of formal variation in their output over many gene
arXiv:2512.13325v2 Announce Type: replace-cross Abstract: Securing digital text is becoming increasingly relevant due to the widespread use of large language models. Individuals' fear of losing contro
Qwen 3.8 - 27B model support This release adds the support of Qwen 3.8 27B. For Apple Silicon devices, Ollama has in particular optimized for maximum performance and output quality suitable for repeat
arXiv:2608.12888v1 Announce Type: new Abstract: Agent-memory systems increasingly buy retrieval quality with structure, transforming raw conversation histories into summaries, embeddings, trees, or kn
arXiv:2608.11341v1 Announce Type: new Abstract: Apollo did not reach the Moon merely because its engineers could solve difficult equations. It succeeded by turning a distant ambition into a mission ar
arXiv:2507.15100v3 Announce Type: replace-cross Abstract: Natural Language Inference (NLI) determines whether a premise entails, contradicts, or is neutral with respect to a hypothesis. The task is of
arXiv:2608.11219v1 Announce Type: new Abstract: Automatic Prompt Optimization (APO) often rewrites prompts monolithically, which can improve one behavior while degrading others. We present SAPO, a seg
arXiv:2608.11624v1 Announce Type: cross Abstract: Persuasion is a core dynamic of natural language communication, shaping how large language models (LLMs) update beliefs, resolve disagreements, and re
SpaceXAI today released Grok 4.6, a large language model that it says can outperform Anthropic PBC’s Claude Fable 5 in some areas. SpaceXAI was known as xAI until last month. The Elon Musk-founded art
We’re working with an initial group of customers to understand where this speed makes the biggest difference, and how those learnings can inform our products over time. If your business requires front
arXiv:2608.10764v1 Announce Type: new Abstract: Counterfactual video understanding evaluates whether models grasp physical and commonsense regularities. However, existing multiple-choice question (MCQ
The model punches above its weight, outperforming Gemma 4 E2B and Ministral 3 3B across a broad range of visual understanding benchmarks and delivers particularly strong results on document understand
arXiv:2608.11013v1 Announce Type: new Abstract: Text-only training is a popular paradigm in zero-shot video captioning, where the video distribution is not available to the model during training, lead
arXiv:2608.07651v1 Announce Type: new Abstract: Large language models (LLMs) show promise in medical image interpretation but suffer from hallucination, limited accuracy, and run-to-run inconsistency.
arXiv:2608.07584v1 Announce Type: new Abstract: Vision-language models (VLMs) have made rapid progress in visual perception and increasingly support real-world tasks that depend on images. Many such t
DeepSeek V4 Flash 0731 is now available to fine-tune on Together AI. Specialize it for coding, tool use, and your own domain with SFT or DPO, then deploy the fine-tuned model on Together AI for produc
arXiv:2608.09779v1 Announce Type: cross Abstract: Answering complex conditional questions using Large Language Models (LLMs) and Retrieval-Augmented Generation (RAG) remains a challenge, particularly
arXiv:2608.08652v1 Announce Type: cross Abstract: We present LegoLM{}, a structured weight-sharing compression framework for large language models grounded in a systematic study of why global weight s
arXiv:2608.09253v1 Announce Type: new Abstract: LLM agents are increasingly equipped with skills to perform complex tasks through multi-step reasoning and tool use. Although skills provide reusable pr
arXiv:2608.09128v1 Announce Type: cross Abstract: LLM agents are increasingly deployed in multi-agent social settings where they must cooperate, negotiate, and adapt to other agents. Measuring and imp
Stealing Reasoning Traces from Proprietary LLM APIs A vanity domain name (stolen-thoughts.com) for a neat paper: Anthropic, OpenAI, and Google return encrypted chain-of-thought blocks to clients that
arXiv:2608.09574v1 Announce Type: new Abstract: LLMs are rapidly embedding themselves into daily life: drafting our emails, managing our schedules, and making decisions on our behalf. As they move fro
arXiv:2503.24191v4 Announce Type: replace-cross Abstract: Content Warning: This paper may contain unsafe or harmful content generated by LLMs that may be offensive to readers. Large Language Models (L
Defensive cybersecurity startup Corma Labs Ltd. today announced it has raised 60 million in seed funding to build a foundation model purpose-built for security defense. Founded in 2025, Corma runs off
arXiv:2608.06578v1 Announce Type: new Abstract: Frontier language models are trained using distinct data, objectives, and safety pipelines. Whether these differences produce measurably different behav
arXiv:2608.07167v1 Announce Type: new Abstract: Giving an AI agent the ability to send emails, query databases, or execute commands is useful--until the agent is tricked into doing something it should
Hey everyone ! Quick share from the cyber + local LLM side of things that I found interesting. During this week’s hacker summer camp, an AI researcher and reverse malware engineer veteran 'lordx64' on
Research: SQLite compressed text-history prototypes I'm perennially interested in options for storing revision histories in relational databases. While out on a dog walk I had a new idea: how about ta
The best 'raw' frontier model for document parsing is gemini 3 flash, but the issue is that since then the flash models have gotten 3x more expensive while flatlining on visual recognition across comp
OpenAI Group PBC today disclosed that one of its unreleased large language models may pose a significant cybersecurity risk. The algorithm, which is known as Astra, was first detailed last week. OpenA
arXiv:2608.05238v1 Announce Type: new Abstract: Training multimodal models to align time series with language runs into a self-supervision trap. The usual recipe asks an LLM to read a series and write
arXiv:2608.05715v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly deployed as planners in robotic systems, where they translate natural-language commands into executable
OpenAI says it is pausing 'internal activities' around an in-development AI model, Astra, because it doesn't yet meet new security standards the company is putting in place. The announcement follows i
arXiv:2606.21155v2 Announce Type: replace Abstract: Attorneys, judges, and pro se filers increasingly use AI to draft legal documents, yet these tools frequently fabricate citations. Despite predictio
anyone confused about neurosymbolic AI—and its recent enormous victory—should read this. complete and total vindication for what I have been saying here all along. (see also my essays on Claude Code a
arXiv:2608.04030v1 Announce Type: cross Abstract: Generative artificial intelligence (AI) has transformed text-to-image synthesis, yet its ability to represent specialized engineering domains remains
arXiv:2608.04463v1 Announce Type: new Abstract: Prior work on LLM conformity largely measures discrete answer flips under verifiable labels. Open-ended revisions require a different measurement strate
arXiv:2608.03070v1 Announce Type: cross Abstract: Frontier AI model developers increasingly rely on layered safeguards to prevent catastrophic misuse, but little public evidence exists on how much pro
arXiv:2608.03532v1 Announce Type: new Abstract: Large language models are increasingly deployed in multilingual contexts, yet safety alignment and bias evaluation remain overwhelmingly English-centric
arXiv:2608.02642v1 Announce Type: cross Abstract: Accelerating scientific discovery is among the most consequential applications of AI, and computational biomolecular simulation stands out as a partic
arXiv:2608.03109v1 Announce Type: new Abstract: Plant root phenotyping is fundamental to understanding below-ground structures, optimizing crop management, and improving agricultural sustainability. T
arXiv:2608.03401v1 Announce Type: cross Abstract: Large language models often reason at length before answering, increasing cost and latency. Prompts and trained settings can shorten this reasoning, b
arXiv:2608.03095v1 Announce Type: new Abstract: We present VIVID (Vietnamese Idioms for Validation and Interpretation Depth), the first systematic benchmark for evaluating culturally grounded figurati
arXiv:2608.01046v1 Announce Type: new Abstract: The rapid spread of large language models (LLMs) across the web raises concerns about misinformation, academic integrity, automated content manipulation
arXiv:2602.01132v2 Announce Type: replace Abstract: Tasks such as solving arithmetic equations, evaluating truth tables, and completing syllogisms are handled well by large language models (LLMs) in t
arXiv:2608.02071v1 Announce Type: new Abstract: Attention-only dynamical theories model Transformer residual directions as particles aggregating on a sphere. We extend this framework by incorporating
Remember OpenAI tripled its score on ARC-AGI with a harness fix? We fixed harness for Kimi K3 on CyberGym E2E: 2x better at vulnerability detection, 3x at patching K3 is SOTA cyber-defense model you c
arXiv:2608.00023v1 Announce Type: new Abstract: Social simulations built from language-model agents need role-conditioned behavior that can be checked before agents are placed into a simulated populat
AFAIK the most significant breakthrough since 2017 besides scaling old ideas was broadening from base models into larger systems that incorporate symbol/manipulating entities like harnesses, tools, an
arXiv:2607.28631v1 Announce Type: new Abstract: AI Scientist systems capable of autonomous research have the potential to significantly accelerate scientific discovery. However, evaluating and compari
arXiv:2607.28634v1 Announce Type: new Abstract: The estimation of item difficulty plays a key role in both formative assessment and large-scale high-stakes summative assessments. This study explores h
arXiv:2607.29082v1 Announce Type: new Abstract: Child malnutrition remains a major public health challenge in low- and middle-income countries, particularly in South Asia, where early identification o
Chinese tech giant Alibaba released what it says is its largest and 'most capable AI model to date,' claiming performance rivaling the best systems from US frontier labs Anthropic and OpenAI, as well
You probably used @FireworksAI_HQ this week. The cool part is that you just did not know you did. 🎆 Open-source models are free, sure... but the hard part is tailoring them so they perform best on you
3/ here's the part that makes it non-optional: the same agent that will do whatever it takes to solve a problem will also walk straight out of a sandbox you thought was locked down. We watched exactly
DeepSeek V4 Flash: Preview → 2026-07-31 Benchmark Preview 0731 Δ Terminal Bench* 56.9 82.7 +25.8 Toolathlon 51.8 70.3 +18.5 NL2Repo — 54.2 new Cybergym — 76.7 new DeepSWE — 54.4 new Agent Last Exam —