Knowledge catalogue
arXiv:2606.10571v1 Announce Type: cross Abstract: Adversarial examples reveal vulnerabilities in Vision-Language Pre-training (VLP) models and provide insights for improving robustness. A key property
arXiv:2606.09950v1 Announce Type: new Abstract: Averaging a neural network over its random parameters and marginalizing a Gaussian sector are the same operation, the Schur complement of the eliminated
arXiv:2606.10931v1 Announce Type: new Abstract: Warning: This paper contains several toxic and offensive statements. Modern large language models (LLMs) are typically aligned through large-scale post-
arXiv:2606.10651v1 Announce Type: new Abstract: We introduce Kwai Keye-VL-2.0-30B-A3B, an open-source Mixture-of-Experts (MoE) multimodal foundation model designed to advance long-video understanding
arXiv:2606.10956v1 Announce Type: new Abstract: The deployment of Large Language Model (LLM) agents for computer automation is accelerating, yet their ability to navigate complex, professional-grade p
arXiv:2606.11074v1 Announce Type: cross Abstract: With the widespread deployment of Multimodal Large Language Models (MLLMs) in social interaction, understanding and controlling their behavior under c
arXiv:2606.09956v1 Announce Type: cross Abstract: The rapid adoption of LLM-powered code generation has dramatically accelerated software development, yet effective verification methods remain severel
arXiv:2606.11107v1 Announce Type: cross Abstract: Clinicians diagnose brain tumors by synthesizing patient symptoms, medical history, and quantitative imaging data from modalities such as MRI and CT s
arXiv:2606.10340v1 Announce Type: new Abstract: Humanoid whole-body control has made significant progress in recent years, yet existing approaches remain limited to few-skill policies with heavy rewar
arXiv:2606.10285v1 Announce Type: new Abstract: OpenRTLSet introduces the largest fully open-source dataset for hardware design, offering over 131,000 diverse Verilog code samples to the research comm
arXiv:2606.09962v1 Announce Type: cross Abstract: Continuous diffusion for categorical data is a framework belonging to the diffusion family and aiming at generating discrete data. The scientific inte
arXiv:2606.10369v1 Announce Type: new Abstract: As large language models (LLMs) continue to scale, it becomes increasingly challenging to grow model capacity under fixed computation budgets. We propos
arXiv:2606.09890v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed as autonomous agents capable of executing multi-step action trajectories toward a given objecti
arXiv:2606.10937v1 Announce Type: cross Abstract: AI compilers aggressively rewrite computation graphs through normalization, lowering, and optimization, making it difficult to track the provenance of
Really enjoyed reading the Microsoft MAI-Thinking-1 'Building a Hill Climbing Machine' paper. Amazing they publicly released all the info needed to train a frontier model, down to hparams. I also thou
arXiv:2606.10949v1 Announce Type: new Abstract: Persistent memory systems promise to make LLMs more helpful by storing user beliefs over time. We show they also make models less correct by systematica
arXiv:2606.10348v1 Announce Type: new Abstract: Object navigation requires an agent to locate a target in an unknown environment through visual observations. Existing methods typically rely on open-vo
arXiv:2606.10917v1 Announce Type: new Abstract: Although Large Language Model (LLM) agents have demonstrated strong performance on complex tasks, their learning is often limited by inefficient interac
arXiv:2606.11016v1 Announce Type: new Abstract: We ask whether large language models (LLMs) merely imitate rationales when choosing between two options, or whether their choices reflect a systematic u
arXiv:2606.10279v1 Announce Type: new Abstract: Supervised fine-tuning with synthetic rationale data is widely assumed to improve language model performance on clinical prediction tasks by teaching mo
arXiv:2606.09853v1 Announce Type: new Abstract: A central objective in multimodal learning is to capture synergy: task-relevant information that arises only from the joint use of multiple modalities,
arXiv:2606.11184v1 Announce Type: new Abstract: Contact-rich manipulation requires robots to continuously perceive and regulate evolving physical interactions under dynamic contact transitions or comp
arXiv:2606.10747v1 Announce Type: new Abstract: As AI systems built from multiple language-model agents become more common, they are increasingly used to make decisions together: discussing, negotiati
The Model Lab vs Agent Lab distinction is one of the clearest frameworks I've seen for understanding where AI value actually lives right now. TL;DR from @latentspacepod: • Model Labs compete on capabi
arXiv:2606.11117v1 Announce Type: cross Abstract: Designing FPGA-based accelerators for modern artificial intelligence workloads requires exploring a large and complex hardware design space that invol
arXiv:2606.10457v1 Announce Type: new Abstract: Decision rules that enterprise experts apply tacitly -- in auditing, compliance, and contract review -- can be systematically recovered and improved thr
arXiv:2606.10912v1 Announce Type: cross Abstract: Deepfake speech detectors often output a single score without explaining why an audio sample is flagged, where in the signal the evidence lies, or wha
arXiv:2606.10267v1 Announce Type: cross Abstract: Hierarchical vision-language-action (Hi-VLA) systems have emerged as a promising paradigm for complex robot manipulation, by using high-level VLM plan
arXiv:2501.14717v2 Announce Type: replace Abstract: Table modeling has progressed for decades. In this work, we revisit this trajectory and highlight emerging challenges in the LLM era, particularly t
arXiv:2512.06343v3 Announce Type: replace-cross Abstract: Reward models are central to Large Language Model (LLM) alignment within the framework of RLHF. The standard objective used in reward modeling
arXiv:2606.09932v1 Announce Type: cross Abstract: Supervised Fine-Tuning (SFT) followed by Reinforcement Learning (RL) has become a standard pipeline for Large Language Model (LLM) post-training. SFT
arXiv:2606.11129v1 Announce Type: new Abstract: We introduce WorldOlympiad, a benchmark for diagnosing video-based world models across physical faithfulness, geometric consistency, and interaction fid
arXiv:2606.09037v1 Announce Type: new Abstract: Interior permanent magnet synchronous motor (IPMSM) design requires balancing conflicting objectives and multi-physics constraints, while modern optimiz
arXiv:2606.08093v1 Announce Type: new Abstract: Pathology is the cornerstone of modern medicine, where accurate decision-making relies heavily on evidence-based practices. While artificial intelligenc
arXiv:2606.08247v1 Announce Type: cross Abstract: Acute asthma risk assessment requires rapid interpretation of respiratory sounds, oxygenation, airflow limitation, speech ability, work of breathing,
arXiv:2606.08214v1 Announce Type: new Abstract: Flexible robotic automation requires systems that interpret operator intent, verify physical feasibility, and recover from execution failures across bot
arXiv:2606.08539v1 Announce Type: new Abstract: AI agents increasingly take consequential actions -- shell commands, cloud operations, and arbitrary tool-calls -- so a trust layer must decide, per act
arXiv:2507.09092v2 Announce Type: replace Abstract: With the intervention of machine vision in our crucial day to day necessities including healthcare and automated power plants, attention has been dr
arXiv:2606.07643v1 Announce Type: cross Abstract: Recent advances in Omni-Multimodal Large Language Models (Omni-MLLMs) have enabled strong integration of vision, audio, and language. However, their 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:2606.07538v1 Announce Type: cross Abstract: Large language model (LLM)-based agents provide a novel paradigm for the automated processing of remote sensing(RS) data. Their success in complex RS
arXiv:2606.07790v1 Announce Type: new Abstract: Multi-agent LLM systems increasingly rely on communication protocols for coordination, yet their robustness under adversarial and structural constraints
arXiv:2606.08893v1 Announce Type: cross Abstract: A small transformer encoder is trained to map Terminal-Wrench trajectories onto a unit sphere where embedding distance approximates the L_1 distance b
arXiv:2606.08169v1 Announce Type: cross Abstract: Enabling robots to understand and execute tasks from natural language commands while maintaining data efficiency remains challenging. Foundation model
Claude Fable 5, Anthropic’s latest frontier model, is now generally available on Google Cloud. This launch is the latest proof point of our ongoing commitment to bring the industry's latest models str
arXiv:2606.09520v1 Announce Type: cross Abstract: Can a general-purpose large language model design molecules with the precision of a seasoned chemist? Current LLM-based frameworks answer this questio
arXiv:2603.04177v2 Announce Type: replace-cross Abstract: LLM coding agents can generate working code, but their solutions often accumulate complexity, duplication, and architectural debt. Human devel
arXiv:2606.09084v1 Announce Type: cross Abstract: Tool-using LLM agents interact with the world through actions that persist state in artifacts (e.g., workspace files or logs). Consequently, jailbreak
arXiv:2606.09672v1 Announce Type: new Abstract: Ask a pretrained biomedical language model whether 'cortisol 28 ug/dL' and 'stock-market volatility' are related, and it returns a cosine similarity of
arXiv:2602.22629v2 Announce Type: replace Abstract: Most existing 3D assembly methods treat the problem as pure pose estimation, rearranging observed parts via rigid transformations. In contrast, huma
arXiv:2606.07708v1 Announce Type: cross Abstract: We introduce a dataset and benchmark for cross-view urban traffic perception built from synchronized ego-centric bicycle videos and aerial drone video
arXiv:2606.09572v1 Announce Type: cross Abstract: Vision-language-action models have shown strong promise for robot manipulation, yet raw language is primarily needed to specify task intent rather tha
arXiv:2606.09142v1 Announce Type: cross Abstract: Egocentric vision offers a first-person view of human perception and decision making, yet its potential for traffic-safety prediction remains underexp
To defend against the growing range of AI-accelerated threat actors, organizations need to be able to respond faster to outpace the adversary.Recently, we announced Google AI Threat Defense, an automa
arXiv:2606.08068v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems often fail to reliably outperform a single strong model equipped with best-of-N sampling. We argue that a
arXiv:2508.11874v2 Announce Type: replace-cross Abstract: Designing polynomial-time algorithms for approximate Nash equilibria (ANE) with provable worst-case guarantees is a fundamental open problem i
arXiv:2606.08525v1 Announce Type: new Abstract: Reward models play a pivotal role in reinforcement learning (RL) and multi-modal trajectory selection for autonomous driving. However, acquiring such re
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:2606.09475v1 Announce Type: new Abstract: Work on `emergent misalignment' shows that finetuning LLMs on narrow tasks can induce broadly misaligned behavior. This supports the `persona selection'
🚨 Fable 5 is something to pay attention to. This is another 'I had early access to the new Mythos-class Anthropic model and I want to tell you what I thought of it' post. I know, I know, it's annoying