Knowledge catalogue
arXiv:2506.07406v3 Announce Type: replace-cross Abstract: Understanding the internal representations of large language models (LLMs) is a central challenge in interpretability research. Existing featu
arXiv:2605.06142v2 Announce Type: replace-cross Abstract: When people recount personal memories, they often refer to people, places, and events indirectly, relying on con-textual cues rather than expl
arXiv:2607.03316v1 Announce Type: cross Abstract: Agentic code review, where autonomous agents provide code review comments on pull requests, is increasingly integrated into development workflows, yet
arXiv:2504.20412v3 Announce Type: replace-cross Abstract: Fuzzing frameworks like syzkaller have uncovered thousands of Linux kernel crashes, many of which are critical and security-sensitive. However
arXiv:2607.03166v1 Announce Type: cross Abstract: Template-based contrastive synthesis is scalable, but its candidates often differ only in a few entity-slots while sequence-level optimization spreads
arXiv:2607.02609v1 Announce Type: cross Abstract: For decades, data engineering has developed mature architectural principles for integrating, governing, validating, cataloging, and serving organizati
arXiv:2603.11784v2 Announce Type: replace Abstract: As scaling laws push the training of frontier large language models (LLMs) toward ever-growing data requirements, training pipelines are approaching
arXiv:2607.03381v1 Announce Type: cross Abstract: Scientific papers follow rhetorical structures that organize content into sections such as Introduction, Methods, Results, and Discussion. Automatical
arXiv:2607.02909v1 Announce Type: cross Abstract: Taxonomies provide key information about the semantic relationships between concepts and the inherent organization of vision and language. Despite the
arXiv:2506.01254v2 Announce Type: replace Abstract: FastText remains a practical choice for industrial word representation because it can synthesize vectors for out-of-vocabulary words from character
arXiv:2607.03847v1 Announce Type: new Abstract: Understanding why discovered scenarios become critical in scenario-based testing is essential for effectively leveraging them in decision-making systems
arXiv:2607.03957v1 Announce Type: cross Abstract: Language models can reach the right normative verdict for the wrong reason. We introduce NormWorlds-CF, a solver-verified environment for counterfactu
arXiv:2509.19833v4 Announce Type: replace-cross Abstract: The United Nations' Sustainable Development Goals (SDGs) provide a globally recognised framework for addressing major societal, environmental,
arXiv:2601.11049v2 Announce Type: replace-cross Abstract: We examine whether large language models (LLMs) can predict biased decision-making in conversational settings, and whether their predictions c
arXiv:2607.03730v1 Announce Type: new Abstract: Conversational agents are increasingly embedded in human collaborative work, yet they remain fundamentally passive and reactive: they respond to explici
arXiv:2601.09097v3 Announce Type: replace Abstract: Multi-constraint planning involves identifying, evaluating, and refining candidate plans while satisfying multiple, potentially conflicting constrai
arXiv:2607.02932v1 Announce Type: cross Abstract: Privacy is an important challenge when users interact with AI chatbots, since users may share sensitive information, explicitly or implicitly, and AI
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:2607.04244v1 Announce Type: new Abstract: This report describes our approach to the Efficient Qwen Competition, where the goal is to enable low-latency serving of Qwen3.5-4B on a resource-constr
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
arXiv:2607.03502v1 Announce Type: cross Abstract: Frontier LLMs can perform multi-step reasoning over content-free filler tokens like dots or counting sequences, producing correct answers with no visi
arXiv:2607.03591v1 Announce Type: cross Abstract: Recent studies on multimodal traffic accident understanding have mainly relied on infrastructure-camera footage, satellite imagery, or structured cras
arXiv:2607.04261v1 Announce Type: new Abstract: Current Legal Judgment Prediction (LJP) is constrained by its reliance on post-hoc judicial materials, increasing the likelihood that models perform ret
arXiv:2607.03377v1 Announce Type: cross Abstract: The rapidly growing repository of publicly available large language models (LLMs) presents significant challenges for systematic management and quanti
This morning I released sqlite-utils 4.0, the 124th release of that project and the first major version bump since 3.0 in November 2020. In addition to some small but significant breaking changes (des
arXiv:2604.00660v2 Announce Type: replace-cross Abstract: Modern data warehouses extend SQL with semantic operators that invoke large language models on each qualifying row, making per-row inference o
arXiv:2607.02807v1 Announce Type: new Abstract: Long-running coding agents such as autoresearch can persistently discover optimizations for open-ended problems. However, they tend to converge onto a s
arXiv:2607.05131v1 Announce Type: new Abstract: Among the five primary human senses, tactile is arguably the most fundamental to survival, as it enables the perception of physical contact and interact
arXiv:2607.05001v1 Announce Type: cross Abstract: Cyber Threat Intelligence (CTI) reports are predominantly unstructured, heterogeneous, and noisy, which limits their direct usability for automated an
arXiv:2510.08048v4 Announce Type: replace-cross Abstract: Query-product relevance prediction is fundamental to e-commerce search and has become even more critical in the era of AI-powered shopping, wh
arXiv:2607.03953v1 Announce Type: cross Abstract: This study independently replicates and extends the Natural Language Tools (NLT) framework of Johnson et al.~(2025), which questions the use of struct
this is a great approach, seeing this more @flymy_ai also does this when you build an agent via their api, they'll build a deterministic reusable workflow, except for where you need models we built th
arXiv:2607.03835v1 Announce Type: cross Abstract: Converting a SPICE netlist into a human-readable schematic is a longstanding problem in electronic design automation: simulators and machine-learning
The web is complex, open-ended, and constantly changing, making it challenging to scale training data for visual web agents. Existing data collection attempts remain limited to offline trajectories fo
arXiv:2607.05132v1 Announce Type: cross Abstract: As large language models are deployed as autonomous agents that communicate intentions before acting, a critical safety question is whether agents tha
arXiv:2607.03158v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to implement algorithms from research manuscripts, but papers often leave implementation choices im
Release b9892 is a version identifier for llama.cpp, an open-source C/C++ framework for running large language model inference on consumer hardware. This specific build (b9892) represents a snapshot o
tencent/Hy3 New Apache 2.0 licensed model from Tencent in China: Hy3 is a 295B-parameter Mixture-of-Experts (MoE) model with 21B active parameters and 3.8B MTP layer parameters, developed by the Tence
Check out all the amazing work from our @SimonsFdn Collaboration on the Physics of Learning and Neural Computation (https://www.physicsoflearning.org/) presented at the main meeting of @ICMLconf #ICML
// HASTE: tiered skills for ML engineering agents // Why do ML engineering agents keep rediscovering the same techniques on every new task? Because each competition is a cold start. New research intro
The search results don't contain specific details about release b9871. Based on the pattern evident in the search results and the context, here's the summary: B9871 is a release of llama.cpp, an open-
Better Models: Worse Tools Armin reports on a weird problem he ran into while hacking on Pi: The short version is that newer Claude models sometimes call Pi’s edit tool with extra, invented fields in
arXiv:2607.02175v1 Announce Type: new Abstract: Multiple-choice medical benchmarks are increasingly saturated, and recent rubric-based evaluations such as HealthBench have shown that open-ended clinic
arXiv:2607.01934v1 Announce Type: cross Abstract: This work introduces AIriskEval-edu-db2, a new dataset designed to train and evaluate auditors based on LLMs for an explainable pedagogical risk asses
arXiv:2607.02387v1 Announce Type: cross Abstract: NASA and its data centers hold thousands of geoscience datasets and tools like Worldview, Giovanni, the Science Discovery Engine, and Harmony. Finding
arXiv:2607.01433v1 Announce Type: new Abstract: Divergent thinking is a crucial aspect of creativity, yet large language models (LLMs) tend to consistently generate similar responses to open-ended que
arXiv:2607.01557v1 Announce Type: cross Abstract: Large Language Models (LLMs) often struggle with persuasion in high-stakes scenarios. People's individual personalities and concerns require tailored
arXiv:2607.01436v1 Announce Type: new Abstract: Diffusion language models, which generate text by denoising a token canvas bidirectionally instead of emitting tokens left to right, have become competi
arXiv:2607.01715v1 Announce Type: new Abstract: Existing robust preference optimization for language-model alignment mainly studies pairwise supervision and places robustness at the dataset, prompt, o
Don't train the model, evolve the harness. I read a brilliant blog post from Hugging Face where they took a frozen open model scoring 0% on a hard legal agent benchmark, left its weights alone, and le
arXiv:2607.01276v1 Announce Type: cross Abstract: Embedding models are essential components of modern Information Retrieval (IR) systems, yet they are typically hidden behind APIs. Recent works have s
arXiv:2607.01690v1 Announce Type: new Abstract: Finetuning a language model on documents that are explicitly annotated as fictional results in a model that still actually believes the documents' core
arXiv:2607.01280v1 Announce Type: new Abstract: Programming-by-example systems infer programs from a small set of input-output examples. Robust PBE work usually models wrong examples as samples from a
arXiv:2607.01590v1 Announce Type: new Abstract: Developing high-performance kernels for Neural Processing Units (NPUs) is a critical industry bottleneck, requiring developers to manually navigate impl
I've been going to tech conferences since eternity and I have to say @aiDotEngineer is something else every time I go I meet coolest people, we stay in touch and ship cool things together, it eventual
arXiv:2504.02327v2 Announce Type: replace Abstract: Natural Language to SQL (NL2SQL) aims to translate natural language queries into executable SQL statements, offering non-expert users intuitive acce
arXiv:2607.01241v1 Announce Type: cross Abstract: Existing prompt compression methods treat text as flat token sequences, failing to capture the distributed nature of important information, which is o
arXiv:2607.01764v1 Announce Type: new Abstract: Repository-level vulnerability reproduction is a demanding software engineering (SE) task: an agent must inspect a codebase, infer the input grammar tha
arXiv:2607.01977v1 Announce Type: new Abstract: Ontology learning (OL) aims to automatically construct structured knowledge models from text, yet progress remains fragmented across methods, domains, a
arXiv:2607.01531v1 Announce Type: new Abstract: Learning how an environment behaves from interaction is central to building agents that adapt to unfamiliar tasks. World models learned with deep networ