Knowledge catalogue
arXiv:2606.11270v1 Announce Type: cross Abstract: Distillation of a language model intended to transfer benign behavior to a student model may also transfer undesirable characteristics, if they are pr
arXiv:2606.11275v1 Announce Type: cross Abstract: Rotary Position Embeddings (RoPE) make attention scores position-relative but leave the value pathway position-blind: the message sent by a value toke
arXiv:2606.12387v1 Announce Type: cross Abstract: Large Language Models (LLMs) have democratized database access through Text-to-SQL, but moving from prototypes to production remains difficult. Real d
arXiv:2606.11926v1 Announce Type: cross Abstract: Scientific progress depends on a repeated loop of exploration, experimentation, and abstraction. Researchers test candidate directions, interpret the
arXiv:2606.10525v1 Announce Type: cross Abstract: Indirect prompt injection poses a critical threat to LLM agents that interact with untrusted external data, yet automated attack methods--proven effec
arXiv:2606.10620v1 Announce Type: cross Abstract: Image generation models now produce high-quality static images, yet their ability to represent how a visual world changes over time remains poorly und
Claude Fable 5 thinks document parsing is beneath it It is absolutely crushing on all reasoning-intensive/long horizon benchmarks: SWE-Bench Pro, FrontierCode, GDPval, Runescape, etc. But for document
arXiv:2606.10479v1 Announce Type: new Abstract: Combinatorics is central to Olympiad-level mathematical problem solving, requiring deep discrete reasoning, creative constructions, and rigorous structu
arXiv:2504.02323v4 Announce Type: replace Abstract: Large language models (LLMs) have created new opportunities to assist teachers and support student learning. While researchers have explored various
Day 0 Anthropic Fable 5 in ParseBench: We tested the model's advancements when it comes to document understanding. The model clearly peaks when it comes to adherence to the original text: 📃 Content fa
arXiv:2606.10062v1 Announce Type: new Abstract: Foundation-model agents are increasingly long-lived systems that remember users across interactions, making memorization an explicit deployment-time fun
arXiv:2606.10736v1 Announce Type: cross Abstract: Large online courses generate thousands of student questions directed at conversational AI teaching assistants, yet these interaction logs remain larg
arXiv:2606.10406v1 Announce Type: cross Abstract: We argue that forgetting is not confined to continual learning but is a general optimization phenomenon: during standard training, dominant mini-batch
arXiv:2606.10159v1 Announce Type: cross Abstract: AI is increasingly used to support scientific peer review, from manuscript screening, reviewer assistance to editorial triage. Although such systems p
arXiv:2510.09801v3 Announce Type: replace Abstract: While benchmarks measure the accuracy of LLM-powered agents, they mostly assume full automation, failing to represent the collaborative nature of re
I argued, publicly, AGAINST each of these foolish predictions– and got endless shit for it. Moral: on X, you probably shouldn’t trust the “wisdom” of the crowds. Remember all the AI predictions people
arXiv:2606.10460v1 Announce Type: cross Abstract: Recent large language models (LLMs) have shown rapid progress in reading-based question answering (QA), where evidence is explicitly provided or can b
arXiv:2606.10209v1 Announce Type: new Abstract: Large language models deployed as autonomous agents for enterprise workflows face a key challenge: verbose tool responses from enterprise systems can ca
arXiv:2606.09852v1 Announce Type: cross Abstract: High-quality source code documentation is vital yet often neglected, especially in critical domains like healthcare where reliability and maintainabil
arXiv:2606.10742v1 Announce Type: cross Abstract: External memory has become a core component of modern web agents, enabling long-horizon reasoning through the retrieval of past experiences. However,
arXiv:2606.10929v1 Announce Type: cross Abstract: Task vectors, LoRA, activation steering, and random search around pretrained weights all suggest that learned behaviour can be controlled by linear di
arXiv:2606.09886v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) large language models achieve strong quality with low per-token compute, yet their deployment is often limited by the
arXiv:2606.11009v1 Announce Type: new Abstract: Large language models are increasingly used to adapt math word problems for personalized learning at scale, but it remains an open question whether thos
With SoftBank apparently struggling to get a margin loan against it’s OpenAI shares, it’s maybe time to repost this, from two years ago. The vast majority of my earlier worries remain: 9 reasons that
arXiv:2601.11541v2 Announce Type: replace-cross Abstract: To address the scalability of feedback in computer science while mitigating the privacy and cost limitations of commercial Large Language Mode
arXiv:2505.21457v2 Announce Type: replace-cross Abstract: Active vision, also known as active perception, refers to actively selecting where and how to look in order to gather task-relevant informatio
arXiv:2603.14342v2 Announce Type: replace-cross Abstract: Modern agricultural data is sourced from diverse platforms and spans multiple spatial scales, ranging from ground-level close-up photography t
arXiv:2606.08970v1 Announce Type: new Abstract: Vision-language models (VLMs) with varying performance and resource requirements are widely deployed, making it difficult for users to select the most a
arXiv:2606.08340v1 Announce Type: new Abstract: As language models are increasingly deployed as autonomous agents, they must coordinate with others over long horizons in open-ended interactive tasks.
arXiv:2606.07519v1 Announce Type: cross Abstract: We introduce the novel task of bidirectional small-granularity search between code and text, where the queries are small snippets of text or code and
BREAKING: Anthropic just dropped Claude Fable 5—this is Mythos, made safe for public release. It is the best coding model in the world. We've been testing it internally @every for the last week or so
arXiv:2606.07881v1 Announce Type: new Abstract: Pipeline parallelism is essential for training large neural networks, but existing schedules trade off throughput, memory, and optimization consistency.
arXiv:2505.11189v3 Announce Type: replace Abstract: Large language models (LLMs) can amplify misinformation, undermining societal goals such as the UN SDGs. We study three documented drivers of misinf
arXiv:2606.07613v1 Announce Type: cross Abstract: Visual evidence has long been treated as a reliable form of legal proof, but advances in artificial intelligence (AI) are undermining that assumption.
arXiv:2606.09410v1 Announce Type: new Abstract: Prior work treats structured output as a reasoning tax, but this framing is incomplete: the cost of formatting depends strongly on a model's spare capac
arXiv:2606.08892v1 Announce Type: new Abstract: AI models deployed in critical domains, such as AI safety research, may subtly sabotage our efforts due to misalignment. Diffuse AI Control is a subfiel
arXiv:2606.08367v1 Announce Type: cross Abstract: Most evaluations of LLM agents look like exams: a discrete task, a clean environment, a score in minutes or hours. We argue that this approach is mism
arXiv:2606.09551v1 Announce Type: cross Abstract: Two-server secure inference allows a client to query a hosted large language model (LLM) without revealing prompts or embeddings. Recent GPU systems b
arXiv:2606.08400v1 Announce Type: cross Abstract: Graduate-level research reading report assessment creates a substantial labor burden for educators. While large language models (LLMs) hold great pote
I didn't have early access to today's Claude Fable 5 release, but I've spent the past ~5.5 hours putting it through its paces. My initial impressions are that this is something of a beast. It's slow,
arXiv:2510.12171v2 Announce Type: replace Abstract: Large Language Models have shown strong scientific reasoning ability, but their performance on materials science problems remains less studied. To f
arXiv:2606.08948v1 Announce Type: cross Abstract: Comprehensive estimation of dietary micronutrients from food images could improve clinical nutrition care, but training such models requires large mul
arXiv:2606.07943v1 Announce Type: cross Abstract: Agent skills provide a lightweight mechanism for extending general-purpose agents, but their open format exposes them to skill-poisoning attacks. A pr
arXiv:2606.07711v1 Announce Type: cross Abstract: Memory is the key component for transforming a stateless LLM into a persistent, evolving agent through experience accumulation, long-horizon planning,
arXiv:2606.08529v1 Announce Type: new Abstract: Published agent capability scores conflate what a model can do with what its scaffold lets it do, and the magnitude of this elicitation gap is not well
arXiv:2606.09669v1 Announce Type: new Abstract: Spatial reasoning is a foundational capability for multimodal large language models (MLLMs) to perceive and operate within the physical world. However,
arXiv:2602.03224v2 Announce Type: replace Abstract: Test-time evolution of agent memory represents a pivotal paradigm for advancing AGI, as it strengthens complex reasoning through experience accumula
arXiv:2606.09204v1 Announce Type: new Abstract: We present a reproducible failure mode of safety training in RAG-based LLM recommendation -- the Injection Paradox -- in which prompt injections embedde
arXiv:2606.09287v1 Announce Type: new Abstract: Understanding how transformer representations evolve across layers, not merely what they encode, remains an open problem in mechanistic interpretability
arXiv:2606.07992v1 Announce Type: new Abstract: As the Model Context Protocol (MCP) standardizes tool-calling for autonomous agents, it introduces a critical, unexamined attack surface: the error-hand
arXiv:2501.06659v2 Announce Type: replace-cross Abstract: Many templatized documents are programmatically generated from structured data following a visual template. Such documents include invoices, t
arXiv:2606.07720v1 Announce Type: new Abstract: Large language models (LLMs) have demonstrated remarkable reasoning abilities on mathematical and multi-hop planning tasks. The CoCoNuT (Chain of Contin
arXiv:2606.06990v1 Announce Type: new Abstract: The generation of high-fidelity synthetic Electronic Health Records (EHR) is crucial for advancing medical research while preserving patient privacy. Ho
arXiv:2505.05232v3 Announce Type: replace Abstract: The rapid expansion of chemistry literature poses significant challenges for researchers seeking to efficiently access domain-specific knowledge. To
arXiv:2512.09634v2 Announce Type: replace Abstract: This article presents the creation of an Estonian-language dataset for document-level subjectivity, analyzes the resulting annotations, and reports
arXiv:2602.04894v4 Announce Type: replace-cross Abstract: LLMs are increasingly used for code generation, but their outputs often follow recurring templates that can induce predictable vulnerabilities
arXiv:2512.23128v2 Announce Type: replace-cross Abstract: Web-based agents powered by large language models are increasingly used for tasks such as email management or professional networking. Their r
arXiv:2508.17821v3 Announce Type: replace-cross Abstract: This paper investigates the limitations of the normalization in attention mechanisms. We begin with a theoretical framework that enables the i
arXiv:2606.07479v1 Announce Type: cross Abstract: Turkish idiomatic light verb constructions (LVCs) are challenging for multiword expression processing because they often share the same surface form a
The AI champions strategy of 2023 doesn't work in 2026. Let me give you my very hot take 🔥 (And know that this is anecdotal, and the world of AI changes every 2 heartbeats, so by the time I finish thi