Auto: The AGI Compiler
arXiv:2607.04542v1 Announce Type: cross Abstract: Every LLM agent run re-derives its behavior token by token on a frontier model: brilliant, expensive, slow, and unbounded. We present Auto, a compiler
Knowledge catalogue
arXiv:2607.04542v1 Announce Type: cross Abstract: Every LLM agent run re-derives its behavior token by token on a frontier model: brilliant, expensive, slow, and unbounded. We present Auto, a compiler
arXiv:2607.03007v1 Announce Type: cross Abstract: Recent advances in molecular large language models have led to strong performance on molecular understanding and generation tasks, yet these gains oft
arXiv:2607.05019v1 Announce Type: cross Abstract: In multimodal classification, late-fusion approaches classify concatenated modality-specific features extracted by unimodal neural networks. When moda
arXiv:2607.04577v1 Announce Type: new Abstract: Code models strictly prioritize functional correctness, leaving software energy efficiency as an unoptimized byproduct. Training models to generate ener
arXiv:2607.04293v1 Announce Type: cross Abstract: Building AI Scientist agents with Large Language Models (LLMs) has recently attracted growing attention. Since scientific discovery fundamentally reli
arXiv:2607.03803v1 Announce Type: cross Abstract: The growing demand for image-to-video creation on mobile devices has increasingly focused on cinematic motion effects like bullet time, dolly zoom, sl
arXiv:2501.10711v5 Announce Type: replace-cross Abstract: Code-related benchmarks play a critical role in evaluating large language models (LLMs), yet their quality fundamentally shapes how the commun
arXiv:2508.10031v2 Announce Type: replace-cross Abstract: While Large Language Models (LLMs) have shown significant advancements in performance, various jailbreak attacks have posed growing safety and
arXiv:2607.04179v1 Announce Type: cross Abstract: End-to-end Vision-Language Models (VLMs) show immense potential in autonomous driving. However, standard Supervised Fine-Tuning (SFT) often suffers fr
arXiv:2602.24044v2 Announce Type: replace-cross Abstract: Large Language Model (LLM) adapters enable low-cost model specialization, but introduce complex caching and scheduling challenges in distribut
arXiv:2410.13800v4 Announce Type: replace-cross Abstract: Physically motivated stochastic dynamics are widely used to sample from high-dimensional distributions. However, such samplers often get trapp
arXiv:2607.05147v1 Announce Type: new Abstract: Speculative decoding accelerates Large Language Model (LLM) inference by decoupling draft generation from target verification. While recent parallel dra
arXiv:2607.02571v1 Announce Type: new Abstract: The Segment Anything Model with Concepts (SAM3) heralds a new paradigm for open-vocabulary segmentation through natural language interaction, offering s
arXiv:2607.05252v1 Announce Type: new Abstract: Simulation-Based Inference (SBI) is critical for scientific discovery, with generative models offering a promising path toward efficient inference. Howe
arXiv:2506.03162v3 Announce Type: replace-cross Abstract: The rapid proliferation of surveillance cameras has increased the demand for automated violence detection. While CNNs and Transformers have sh
arXiv:2604.16870v2 Announce Type: replace-cross Abstract: AI agents increasingly call external tools (file system, network, APIs) through the Model Context Protocol (MCP). These tool calls are the age
arXiv:2607.05104v1 Announce Type: cross Abstract: Grokking -- the delayed onset of generalization long after a network has fit its training set - -is usually studied in models too large to read comple
arXiv:2607.02991v1 Announce Type: new Abstract: While multimodal Large Language Models (MLLMs) excel at offline video understanding, an interesting question of how far they are from serving as a real-
arXiv:2607.04344v1 Announce Type: cross Abstract: While Large Vision-Language Models (VLMs) demonstrate remarkable generic capabilities, their clinical reasoning in specialized domains like ocular sur
arXiv:2607.02680v1 Announce Type: cross Abstract: MLLMs have shown strong zero-shot capabilities across diverse inputs such as across images, video, audio, and text. A crucial, yet underexplored, appl
arXiv:2603.17484v2 Announce Type: replace Abstract: Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on l
arXiv:2607.04319v1 Announce Type: new Abstract: A companion paper showed that a transformer's feed-forward layer can be rebuilt from explicit fuzzy set operations - intersection, set-difference, and a
arXiv:2607.04553v1 Announce Type: cross Abstract: We present a bidirectional framework for estimating the energy consumption of text-to-video (T2V) and text-to-video-audio (T2VA) models from architect
arXiv:2607.05031v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used to produce test oracles, the part of a test that decides whether observed behavior is correct. Yet
arXiv:2607.05114v1 Announce Type: cross Abstract: Large Language Models (LLMs) and high-dimensional perception networks increasingly rely on parameter-efficient fine-tuning (PEFT) to adapt to diverse
arXiv:2503.17577v2 Announce Type: replace-cross Abstract: Deepfakes have emerged as a widespread and rapidly escalating concern in generative AI, spanning images, audio, and videos. Among these, audio
arXiv:2601.22054v2 Announce Type: replace-cross Abstract: Scaling has powered recent advances in vision foundation models, yet extending this paradigm to metric depth estimation remains challenging du
arXiv:2607.05376v1 Announce Type: new Abstract: Recent advances in video diffusion models have enabled either long single-view generation through temporal autoregression, or short multi-view synthesis
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:2607.02714v1 Announce Type: cross Abstract: There is no doubt that safety alignment is an essential step in LLM training. However, conceptually it does not distinguish between various domains an
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:2607.03929v1 Announce Type: cross Abstract: Multi-Meta-RAG improves retrieval for multi-hop question answering by filtering a vector store on metadata (the news source) that it extracts from eac
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:2607.03968v1 Announce Type: cross Abstract: Large language models are increasingly deployed as IDE-integrated coding agents that decompose tasks, generate and edit files, run code, and refine ou
arXiv:2210.10619v3 Announce Type: replace-cross Abstract: Reliability measures associated with the prediction of the machine learning models are critical to strengthening user confidence in artificial
arXiv:2607.04017v1 Announce Type: new Abstract: Human object interaction (HOI), gaze pattern, and their anticipation are intricately linked, providing valuable insights into cognitive processes, inten
arXiv:2607.02802v1 Announce Type: cross Abstract: As LLMs are increasingly deployed as autonomous adjudicators in semi-open textual game environments, robust rule adherence becomes critical when user
arXiv:2607.03103v1 Announce Type: cross Abstract: Clinical cardiac imaging pipelines currently deploy separate models for each dataset and modality, incurring redundant training costs and precluding k
arXiv:2607.04694v1 Announce Type: new Abstract: As vision-language models (VLMs) are increasingly applied to medical AI, existing benchmarks mainly focus on evaluating their diagnosis ability over giv
arXiv:2511.07403v2 Announce Type: replace-cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable progress in vision-language tasks, but continue to struggle with spatial rea
arXiv:2507.02950v3 Announce Type: replace-cross Abstract: Large language models (LLMs) may support counseling training, yet evidence from Japanese-language interactions and automated quality ratings r
arXiv:2607.04612v1 Announce Type: cross Abstract: Graphic design editing requires precise manipulation of typography, layout, and visual hierarchy under strict design constraints. Following the introd
arXiv:2607.04034v1 Announce Type: cross Abstract: The language models that underpin agents have seen a rapid rise in performance on function calling benchmarks. However, the metrics used in the traini
arXiv:2411.12030v3 Announce Type: replace Abstract: In this paper, the method of gaps, a technique for deriving closed-form expressions in terms of information measures for the generalization error of
arXiv:2607.02521v1 Announce Type: cross Abstract: SwiGLU is the dominant MLP activation in modern large language models, yet its intermediate tensor materialization costs 9-37% of MLP execution time.
arXiv:2607.05089v1 Announce Type: new Abstract: Video reasoning requires models to identify and verify temporally localized evidence within long video sequences. Recent Video Large Language Models (Vi
arXiv:2607.02593v1 Announce Type: cross Abstract: While knowledge distillation (KD) is widely adopted for training lightweight models by leveraging supervision from larger teacher models, relying sole
arXiv:2605.25706v2 Announce Type: replace Abstract: Referring expression comprehension (REC) aims to localize a target object within an image based on a given expression. Although recent advances in v
arXiv:2607.03904v1 Announce Type: new Abstract: Pulsar timing arrays (PTAs) provide a unique window into nanohertz gravitational waves (GWs), but extracting astrophysical parameters from noisy, long-b
arXiv:2607.04510v1 Announce Type: cross Abstract: Emergent misalignment (EM) -- the broad misbehaviour a language model acquires after fine-tuning on narrow harmful data -- is mediated in Qwen2.5 mode
This post discusses how observing Claude's internal activation patterns (J-space) reveals the model's hidden reasoning processes, such as detecting code bugs and analyzing images, even when these step
Reporting benchmark results as a single scalar percentage is insufficient for meaningful evaluation of model performance. Comprehensive benchmark reporting should include efficiency metrics alongside
The automotive industry is at a pivotal crossroads as it hits the gas on adopting new technology. The era of the traditional connected vehicle has shifted into the age of the software-defined vehicle
arXiv:2607.01400v1 Announce Type: cross Abstract: Deep multimodal brain-encoding models now predict fMRI responses to naturalistic video with high accuracy. Whether their predicted neural signals also
arXiv:2602.19127v2 Announce Type: replace Abstract: With the rapid advancement of agent-based methods in recent years, Agentic RAG has undoubtedly become an important research direction. Multi-hop rea
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:2607.01973v1 Announce Type: cross Abstract: Vision-Language Models (VLMs) are increasingly applied in medical tasks such as pathology description, report generation, and visual question answerin
arXiv:2607.01959v1 Announce Type: cross Abstract: We propose a model agnostic methodology to measure lag relevance in machine learning forecasting models applied to univariate time series. Particularl
arXiv:2607.01272v1 Announce Type: cross Abstract: Deploying 3D point cloud analysis in privacy-sensitive, resource-constrained settings faces two barriers: data cannot be centralized, and models must
arXiv:2607.01600v1 Announce Type: cross Abstract: As large language models (LLMs) are deployed as communicating agents, does inter-agent communication cause outputs to converge? We introduce BOUNDARY_