Knowledge catalogue
arXiv:2607.20466v1 Announce Type: new Abstract: Rigorous benchmarks have driven progress in autonomous GPU kernel performance optimization by establishing a shared target to hillclimb on, but no equiv
arXiv:2607.20723v1 Announce Type: cross Abstract: This work presents LeakyLMs, a set of attacks that leak proprietary model, architecture, and deployment information from production language models. L
arXiv:2607.20864v1 Announce Type: cross Abstract: Position bias in multiple-choice LLM evaluation is widely cited as a confound in capability comparisons, but published measurements rely on single ans
arXiv:2607.21022v1 Announce Type: new Abstract: Improving video captioning quality typically demands retraining large vision-language models, an expensive and often impractical requirement. Existing t
arXiv:2602.10226v2 Announce Type: replace-cross Abstract: Optimizing large-scale machine learning systems, such as recommendation models for global video platforms, requires navigating a massive hyper
arXiv:2607.18496v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly used for a range of software, hardware and human-centered security tasks. Consequently, LLM perf
We benchmarked Opus 5 comprehensively on document understanding through ParseBench. It is roughly on par with Opus 4.8 - it does a few points worse on dense tables, but does slightly better on parsing
arXiv:2607.17075v2 Announce Type: replace-cross Abstract: The advent of LLMs has significantly changed the research on privacy policy and data compliance analysis by enabling tasks that previously req
Announcing OpenWorker! An open-source agent that doesn't just chat with you, but delivers finished work -- like hand you a polished document, send a slack message, or update a calendar entry. Ask it t
arXiv:2607.19847v1 Announce Type: cross Abstract: Predicting missing cell values in tabular data is a fundamental problem in data cleaning. While state-of-the-art reasoning models show great promise i
arXiv:2607.15434v3 Announce Type: replace-cross Abstract: Multi-agent systems routinely place one AI agent in authority over another. When a subordinate refuses a task, the manager chooses the outcome
I kept re-wiring the same RAG plumbing on every project, so I turned it into a clean starter and open-sourced it. Upload a PDF, ask questions, and get answers with page-level source citations. It runs
LTX Desktop v1.1.0 just shipped with some big updates. Apple Silicon Macs can generate video locally now, there's a built-in LoRA/IC-LoRA library you can browse and apply from inside the app with per-
arXiv:2605.05598v2 Announce Type: replace Abstract: The proliferation of large language models (LLMs) in educational settings has paradoxically undermined the cognitive processes they purport to suppo
arXiv:2607.20216v1 Announce Type: cross Abstract: Malware analysis demands rapid interpretation of complex detonation reports spanning filesystem, network, and process behaviours. While large language
arXiv:2607.20328v1 Announce Type: cross Abstract: This study empirically analyzed generative AI as an emerging discovery pathway to academic library resources. Utilizing web analytics from August 2023
arXiv:2607.19967v1 Announce Type: cross Abstract: Shippers are beginning to delegate carrier selection to large language model (LLM) agents. We ask what such delegation does to a freight matching mark
“Generate a fake, but believable, witty Churchill insult at a party and explain the context. It should be very clever and original” This time, I think GPT 5.6 Sol Pro wins, but Fable is good too, and
Disclosure: I work at NuMind, the team that trained NuExtract3. NuExtract3 is an Apache-2.0, open-weight 4B VLM based on Qwen3.5-4B. It is specialized for document understanding rather than general ch
This story is wild. The short version: OpenAI were running a cybersecurity test against an unreleased model, with the model's guardrail features turned off. Rather than solve the test, the model broke
As AI models are now finding vulnerabilities faster than we can fix them, our approach to securing software must be built on highly efficient and capable models. Which brings us to our third (!) model
LWiAI Podcast #249 (June 17 2026) reports that Anthropic halted access to Fable 5 and Mythos 5 following a U.S. government order over alleged jailbreaks, prompting debate on export controls and the fe
very notable trajectory comparison writeup here buried in the RLM paper from @a1zhang and @lateinteraction. an open secret of 'frontier' model training is that even without training on test, you can b
Huge launch from @tryramp. Different steps in an agent workflow can use different models. This can help reduce costs significantly without sacrificing performance. Model routing will become a core par
Automated lint: 20 errors, 8743 warnings, 3 info
arXiv:2601.22830v2 Announce Type: replace Abstract: Reliable environmental perception remains one of the main obstacles for safe operation of automated vehicles. Safety of the Intended Functionality (
arXiv:2601.02023v2 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) increasingly utilize massive context windows as working memory for autonomous tasks, their reliability fluctua
arXiv:2607.13189v1 Announce Type: cross Abstract: We present RAGthoven, our system for SemEval-2026 Task 1 (MWAHAHA), Subtask A (multilingual constrained humor generation in English, Spanish, and Chin
BREAKING: Inkling by @thinkymachines is 9th overall on Agentic Web App Arena by Design Arena with an Elo of 1257 It's an open-weight model in the same performance band as Claude Opus 4.6 by @Anthropic
arXiv:2607.12195v1 Announce Type: cross Abstract: Semantic memory retrieval can be conceptualized as navigation through conceptual space. We compared semantic search dynamics between humans and three
arXiv:2607.12056v1 Announce Type: new Abstract: Online shopping is increasingly shifting toward a model in which AI agents independently search for products, compare options, evaluate constraints, and
Automated lint: 26 errors, 6728 warnings, 3 info
What it is: ATH-MaaS/OvisOCR2 - a 0.8B document-parsing VLM post-trained from Qwen3.5-0.8B (SFT + RL + OPD), Apache 2.0, runs on vLLM 0.22.1. One prompt per page image -> complete markdown (HTML table
arXiv:2607.12216v1 Announce Type: cross Abstract: Multi-agent and memory-augmented LLM systems often place coordination content, shared state, prior discussion, tool outputs, summaries, and role instr
Running frontier AI in production is demanding — accelerators to manage, latency to hold steady across continents, regulated data to keep in-region, and long-context requests to serve reliably. Claude
In 2026, the public sector is no longer defending a traditional perimeter. Instead, they are defending a complex web of interconnected trust relationships against adversaries that now operate at machi
ChatGPT still has study mode, but rather than /study you now have to type @ study It makes the AI act more like a tutor than a helpful assistant, and some work suggests it is better if you are trying
arXiv:2607.08423v1 Announce Type: new Abstract: The rapid integration of Large Vision-Language Models (VLMs) into critical infrastructure promises to revolutionize personalized healthcare and dietary
arXiv:2607.08602v1 Announce Type: new Abstract: Hepatocellular carcinoma (HCC) is a common malignancy and a leading cause of cancer-related mortality. Current guidelines and staging systems provide co
arXiv:2607.07189v1 Announce Type: new Abstract: Vision-language models (VLMs) and agentic AI have shown strong performance on semantic visual tasks, but it remains unclear whether they can handle the
arXiv:2603.26772v2 Announce Type: replace-cross Abstract: Automated semantic annotation of broadcast television content presents distinctive challenges, combining structured audiovisual composition, d
Here’s a question we hear often at Google Cloud: How do you safely run AI-generated code or untrusted binaries without putting your host application, data, and cloud credentials at risk? In other word
arXiv:2607.06636v1 Announce Type: cross Abstract: Large language models frequently generate code that appears correct on typical inputs yet fails on edge cases, invalid inputs, and other specification
// The Harness Effect // (bookmark it) Now more that ever pay very close attention to the orchestration harness and its effect on costs and performance. This study ran 22 evaluation tasks on six found
arXiv:2607.05614v1 Announce Type: cross Abstract: Document comprehension is a challenging yet impactful task for Multimodal Large Language Models, especially as these systems see growing adoption in r
arXiv:2507.10177v2 Announce Type: replace-cross Abstract: Although Large Language Models (LLMs) have demonstrated significant advancements in natural language processing tasks, their effectiveness in
arXiv:2607.06468v1 Announce Type: new Abstract: We introduce EgoPolice, a carefully curated dataset of real, egocentric police-civilian interactions, sourced from publicly available body-worn camera v
Researchers discovered a HalluSquatting attack that exploits AI tools' tendency to hallucinate package names, which attackers can register to trick AI assistants into running malicious code and assemb
arXiv:2601.12494v3 Announce Type: replace-cross Abstract: Audio large language models (LLMs) enable unified speech understanding and generation, but adapting them to linguistically complex and dialect
- OpenAI continually outperforms Anthropic models on computer use (with Claude, I’m surprised when it works, with Codex, I expect it to work) - when I prompt with Fable 5.5, I feel like I’m motivating
arXiv:2607.05552v1 Announce Type: cross Abstract: Large language models (LLMs) increasingly issue judgments read as binary verdicts, and a growing literature reports such judgments shifting under logi
arXiv:2607.05120v1 Announce Type: cross Abstract: AI agents act on behalf of user prompts, consuming external data and taking actions based on the agent context. Prior research on AI agent security ha
arXiv:2607.05174v1 Announce Type: new Abstract: Language agents, i.e., LLM agents, progress rapidly and are increasingly deployed in production environments. This trend underscores the urgent need for
arXiv:2607.04410v1 Announce Type: new Abstract: We present the AI Wizards submission to EXIST 2026 for multimodal sexism identification in memes. The task is composed of three, increasingly harder sub
arXiv:2607.03691v1 Announce Type: cross Abstract: Coding agents, autonomous systems that use large language models (LLMs) to resolve software engineering tasks, rely on agentic scaffolding: a middlewa
arXiv:2511.17384v2 Announce Type: replace-cross Abstract: While Visual Large Language Models (VLLMs) show great promise as embodied agents, they continue to face substantial challenges in spatial reas
arXiv:2607.03043v1 Announce Type: new Abstract: Understanding camera movement in natural language is critical for training and evaluating video generation models, among other applications. However, we
arXiv:2603.02510v2 Announce Type: replace Abstract: The transition from sequential to parallel computing is essential for modern high-performance applications but is hindered by the steep learning cur
arXiv:2602.20629v3 Announce Type: replace Abstract: As Large Language Models (LLMs) saturate elementary benchmarks, the research frontier has shifted from generation to the reliability of automated ev
arXiv:2607.02921v1 Announce Type: cross Abstract: Quantitative 3D spatial reasoning from egocentric RGB-D video is a critical capability for next-generation wearable assistants. Yet existing benchmark