Knowledge catalogue
arXiv:2605.17691v1 Announce Type: cross Abstract: Automating the classification of negative treatment in legal precedent is a critical yet nuanced NLP task where misclassification carries significant
arXiv:2605.17626v1 Announce Type: new Abstract: Test-time scaling is an important mechanism for improving large language models, especially on tasks with deterministic verifiers. Code translation is a
arXiv:2605.17998v1 Announce Type: cross Abstract: As multi-agent systems move from short interactions to tool-using workflows with specialized roles and persistent state, completion becomes a runtime-
arXiv:2605.17467v1 Announce Type: new Abstract: Large language model-driven multi-agent systems (LLM-MAS) excel at complex tasks, yet unreliable agents remain a key bottleneck to system-level reliabil
arXiv:2605.16859v1 Announce Type: cross Abstract: 3D change detection from multi-view images is essential for urban monitoring, disaster assessment, and autonomous driving. However, existing methods p
arXiv:2605.16911v1 Announce Type: new Abstract: 3D semantic occupancy prediction requires accurate 2D-to-3D feature lifting, yet current methods restrict camera geometry to initial projections. Subseq
This video discusses the architectural need for a continuity layer in long-running AI agents, explaining how agents require persistent memory and state management mechanisms to maintain coherence acro
arXiv:2605.18160v1 Announce Type: cross Abstract: In recent years, multimodal large language models (MLLMs) have achieved remarkable progress, primarily attributed to effective paradigms for integrati
arXiv:2602.04802v2 Announce Type: replace Abstract: Vision-Language Models (VLMs) have achieved impressive performance in cross-modal understanding across textual and visual inputs, yet existing bench
arXiv:2605.16481v1 Announce Type: cross Abstract: Long video understanding requires more than large context windows. It also needs a memory mechanism that decides what visual evidence to retain, keeps
arXiv:2605.18172v1 Announce Type: new Abstract: Leveraging the universal representations of pre-trained LLMs and MLLMs offers a promising path toward brain foundation models. However, visually-evoked
arXiv:2605.18313v1 Announce Type: cross Abstract: Small vision-language models (2-8B) are well-suited for clin- ical deployment due to privacy constraints, limited connectivity, and low-latency requir
arXiv:2601.06943v2 Announce Type: replace-cross Abstract: In real-world video question answering scenarios, videos often provide only localized visual cues, while verifiable answers are distributed ac
arXiv:2605.18749v1 Announce Type: cross Abstract: Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this wo
arXiv:2509.22510v3 Announce Type: replace Abstract: Alignment of Large Language Models (LLMs) is the ability to satisfy desired objectives during generation, which is critical for trustworthy deployme
We were able to sit down with the @GoogleDeepmind team behind the new Gemini Omni Flash model to hear all of their behind-the-scenes stories, memorable moments, and many, many (occasionally embarrassi
arXiv:2605.17637v1 Announce Type: new Abstract: Coding agents are increasingly used as application builders, yet many evaluations still focus on source code, repository-level tests, or intermediate tr
arXiv:2510.16252v2 Announce Type: replace-cross Abstract: Reinforcement learning (RL) for web agents demands environments that are both effective for evaluation and efficient enough for large-scale on
arXiv:2605.17146v1 Announce Type: cross Abstract: Digital twins (DTs) rely on continuous synchronization between physical systems and their virtual counterparts through online parameter estimation und
arXiv:2510.15221v2 Announce Type: replace Abstract: Affective computing has matured rapidly in laboratory settings, yet no prior dataset combines (i) months-to-years of duration, (ii) a naturalistic w
We’re adding new ways for people to identify AI-generated images and understand where they came from. In addition to C2PA Content Credentials, images now also contain a SynthID watermark, and can be i
We’re releasing Nemotron-Labs-Diffusion - the first Tri-mode LM family (3B/8B/14B) that switches between 1⃣Autoregressive, 2⃣Diffusion, and 3⃣Self-Speculation decoding by simply changing the attention
arXiv:2605.18738v1 Announce Type: new Abstract: Medicine is inherently pluralistic. Principles such as autonomy, beneficence, nonmaleficence, and justice routinely conflict, and such ethical dilemmas
At Google I/O, we introduced a unified development toolkit featuring Antigravity 2.0 and the Managed Agents API, giving developers better ways to build locally and deploy securely to the cloud on a sh
arXiv:2605.17795v1 Announce Type: cross Abstract: Learning with noisy labels (LNL) is typically benchmarked by closed-set classification accuracy, yet deployment often requires classifiers to reject o
arXiv:2605.16288v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly used in clinical and care settings. This exploratory study investigates whether LLMs exhibit sycophantic
arXiv:2605.18580v1 Announce Type: new Abstract: Outcome-only evaluation can certify economically unsafe agents: a policy can hit a business KPI while violating deployable behavioral discipline. In hot
arXiv:2601.17887v2 Announce Type: replace Abstract: Long-term memory enables large language model (LLM) agents to support personalized and sustained interactions. However, most work on personalized ag
arXiv:2602.05813v2 Announce Type: replace Abstract: We study adaptive learning rate scheduling for norm-constrained optimizers (e.g., Muon and Lion). We introduce a generalized smoothness assumption u
arXiv:2605.16972v1 Announce Type: cross Abstract: Cultural heritage exhibitions often struggle to sustain attention and support reflective engagement. Physical exhibitions rely on fixed interpretive a
arXiv:2605.18132v1 Announce Type: cross Abstract: Generative 3D models are deployed in gaming, robotics, and immersive creation, making source attribution critical: given a 3D asset, can we identify w
arXiv:2605.16402v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have revolutionized GUI automation, yet their efficacy is largely established on idealized, single-layer interf
arXiv:2605.18115v1 Announce Type: new Abstract: Building a unified visual tokenizer is essential for bridging the gap between visual understanding and generation. Yet existing approaches struggle with
Google Cloud is enhancing its “agent-first” coding platform for developers with the launch of Antigravity 2.0, a new standalone desktop application that enables a full “agent-optimized” user experienc
This post documents a completed Wordle puzzle (#1,794) where the player successfully identified the target word in 3 attempts. The emoji grid shows the color-coded feedback from each guess: gray (inco
This post documents a Wordle puzzle solution (puzzle #1,795) completed in 4 attempts, showing the progression of letter placements and eliminations across guesses before arriving at the final correct
Gemini Omni is built on Gemini's extensive knowledge base of history, science, and culture, enabling it to generate videos with sophisticated contextual understanding. The capability leverages Google'
arXiv:2605.17912v1 Announce Type: cross Abstract: World models have emerged as a central paradigm for embodied intelligence, enabling agents to predict action-conditioned future and reason about envir
Google is going all in on AI-driven shopping even as some competitors back off. At Google I/O, the company unveiled the latest iteration of its AI commerce tools: a 'Universal Cart' that works across
arXiv:2605.16903v1 Announce Type: new Abstract: Open world image segmentation aims to achieve precise segmentation and semantic understanding of targets within images by addressing the infinitely open
xAI has published a blog post detailing how to utilize Grok, their AI assistant, in conjunction with OpenClaw, likely a development framework or tool for integrating AI capabilities. The post was shar
arXiv:2603.09405v2 Announce Type: replace Abstract: Neural Architecture Search (NAS) for object detection is severely bottlenecked by high evaluation cost, as fully training each candidate YOLO archit
arXiv:2605.16699v1 Announce Type: new Abstract: Capped-usage SaaS products -- LLM subscriptions such as Claude Code and ChatGPT, cloud platforms such as Vercel and Cloudflare Workers, corporate benefi
arXiv:2605.16877v1 Announce Type: new Abstract: Zero-shot textual explanations aim to make image classifiers more transparent by probing their internal representations, without relying on task-specifi
arXiv:2605.15708v1 Announce Type: new Abstract: Recent advances in 3D datasets and multimodal models have greatly improved natural language 3D scene understanding. However, most 3D referring segmentat
arXiv:2605.15398v1 Announce Type: cross Abstract: Recent advances in 3D generative editing, particularly pipelines based on 3D Gaussian Splatting (3DGS), have achieved high-fidelity, multi-view-consis
arXiv:2605.15906v1 Announce Type: new Abstract: Image degradations can occur during acquisition, processing, and transmission, altering visual appearance and affecting downstream vision tasks. They ar
arXiv:2605.16090v1 Announce Type: cross Abstract: Large vision-language models (LVLMs) have emerged as a powerful paradigm for multimodal intelligence, but their growing deployment also expands the at
arXiv:2605.15949v1 Announce Type: new Abstract: This paper presents a reproducible and physically feasible dynamic parameter identification framework for CRANE-X7, a low-cost robot arm driven by modul
arXiv:2507.14200v2 Announce Type: replace-cross Abstract: Existing multi-LLM collaboration systems often encounter scalability challenges when integrating new LLMs and tasks, leading to suboptimal per
arXiv:2605.15237v1 Announce Type: cross Abstract: Accelerating applications through the design of hardware accelerators can significantly enhance system performance and energy efficiency. Despite adva
arXiv:2505.21698v3 Announce Type: replace Abstract: Vision-language foundation models achieve promising performance in natural image classification, yet their direct application to medical imaging is
arXiv:2605.15584v1 Announce Type: new Abstract: Vision-language models like CLIP have demonstrated remarkable zero-shot transfer capabilities. However, their susceptibility to imperceptible adversaria
arXiv:2605.15871v1 Announce Type: new Abstract: Toward recursive self-improvement, we investigate LLM agents autonomously designing foundation models beyond standard Transformers. We introduce a dual-
arXiv:2605.15700v1 Announce Type: new Abstract: Automated machine learning pipelines increasingly produce models whose predictions must be explained to end users, auditors, and downstream decision sys
arXiv:2601.03707v2 Announce Type: replace Abstract: Existing UAV vision-and-language navigation (VLN) benchmarks rarely provide realistic aerial scenes, natural process-level instructions, and suffici
arXiv:2602.14896v2 Announce Type: replace Abstract: Large-scale deep learning models are well-suited for compression. Across a variety of tasks, methods like pruning, quantization, and knowledge disti
arXiv:2605.15688v1 Announce Type: cross Abstract: Concept Activation Vectors (CAVs) are a fundamental tool for concept-based explainability in deep learning, yet their practical utility is limited by
arXiv:2605.15768v1 Announce Type: new Abstract: Social simulation provides a compelling testbed for studying social intelligence, where agents interact through multi-turn dialogues under evolving cont
arXiv:2605.15497v1 Announce Type: new Abstract: We study the problem of directly deriving an initial human reenactment from a monocular video of a non-human character. Our goal is not to reconstruct t