Knowledge catalogue
arXiv:2605.10117v1 Announce Type: cross Abstract: Autonomous driving scenes range from empty highways to dense intersections with dozens of interacting road users, yet current 3D detection models appl
arXiv:2605.09544v1 Announce Type: new Abstract: Tool-integrated reasoning has emerged as a promising paradigm for enhancing large language models with external computation, retrieval, and execution ca
arXiv:2605.10194v1 Announce Type: new Abstract: On-policy self-distillation (self-OPD) densifies reinforcement learning with verifiable rewards (RLVR) by letting a policy teach itself under privileged
arXiv:2605.08974v1 Announce Type: cross Abstract: While multimodal large language models (MLLMs) have advanced video understanding, they remain highly prone to hallucinations in dynamic scenes. We arg
arXiv:2605.09862v1 Announce Type: cross Abstract: Graph learning research has increasingly shifted toward continual graph learning (CGL), which better reflects real-world scenarios where graphs evolve
arXiv:2605.10172v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) have achieved remarkable success in general perception, yet complex multi-step visual reasoning remains a per
arXiv:2605.06033v2 Announce Type: replace-cross Abstract: The extent to which Artificial Intelligence (AI) can trigger generalized paradigm shifts in science is unclear. Although some of these technol
arXiv:2605.08478v1 Announce Type: new Abstract: We study how to allocate inference-time compute for competitive programming under fixed budgets. Evaluating 216 Codeforces problems across Divisions 1-3
arXiv:2602.09789v3 Announce Type: replace Abstract: Scaling up model parameters has long been a prevalent training paradigm driven by the assumption that larger models yield superior generation capabi
arXiv:2605.10434v1 Announce Type: new Abstract: Commercial video generation systems such as Seedance2.0 and Veo3.1 have rapidly improved, strengthening the view that video generators may be evolving i
xAI is rolling out Skills on http://grok.com. This new feature lets you create custom skills that Grok can reuse across conversations. Skills run inside Grok’s sandbox environment, so they can edit fi
arXiv:2605.06912v1 Announce Type: new Abstract: The proliferation of generative video technologies has intensified the need for reliable methods to detect and characterize synthetic media. To address
arXiv:2605.07825v1 Announce Type: cross Abstract: Training multimodal large language models has long been limited by the scarcity of high-quality paired multimodal data. Recent studies show that the s
arXiv:2605.07191v1 Announce Type: new Abstract: A recent work shows that Attention Transfer, which transfers only the attention patterns from a pre-trained teacher Vision Transformer (ViT) to a random
Ollama versions prior to 0.17.1 contain a critical out-of-bounds read vulnerability (CVE-2026-7482, CVSS 9.1) that allows remote unauthenticated attackers to leak entire process memory, potentially af
arXiv:2605.07453v1 Announce Type: new Abstract: Ancient and endangered languages pose a unique challenge for NLP: their datasets are inherently scarce, difficult to expand, and built from formulaic co
arXiv:2412.11194v2 Announce Type: replace-cross Abstract: Security vulnerabilities in software can have severe consequences; however, manual vulnerability detection is costly and does not scale, espec
arXiv:2605.06738v1 Announce Type: cross Abstract: Autonomous AI agents now transact at production scale -- 69,000 bots executing 165 million transactions across 50 million USDC in cumulative volume on
arXiv:2605.07250v1 Announce Type: cross Abstract: Recent advancements in visual context compression enable MLLMs to process ultra-long contexts efficiently by rendering text into images. However, we i
arXiv:2510.08638v3 Announce Type: replace-cross Abstract: DINOv2 is routinely deployed to recognize objects, scenes, and actions; yet the nature of what it perceives remains unknown. As a working base
arXiv:2605.07622v1 Announce Type: new Abstract: Gender bias in large language models has primarily been investigated for English, while languages with grammatical or morphological gender remain compar
arXiv:2605.06846v1 Announce Type: cross Abstract: Recent work identifies secret loyalties as a distinct threat from standard backdoors. A secret loyalty causes a model to covertly advance the interest
arXiv:2503.06223v5 Announce Type: replace Abstract: Large Vision-Language Models (VLMs) are increasingly deployed in open-ended environments, where ensuring reliable safety under multimodal inputs is
arXiv:2605.07134v1 Announce Type: cross Abstract: Web agents perceive web pages through an observation space, yet its granularity has remained an underexamined design choice. Existing work treats obse
arXiv:2605.08043v1 Announce Type: cross Abstract: While text-to-image models have made strong progress in visual fidelity, faithfully realizing complex visual intents remains challenging because many
arXiv:2508.04056v2 Announce Type: replace Abstract: Enteric methane measurement from ruminant livestock faces fundamental trade-offs between accuracy and operational feasibility. Existing methods quan
arXiv:2605.07420v1 Announce Type: cross Abstract: Pre-trained models with parameter-efficient fine-tuning (PEFT) have demonstrated promising potential for class-incremental learning (CIL), yet catastr
arXiv:2602.17251v2 Announce Type: replace Abstract: Electroencephalography (EEG) foundation models (EFMs) have shown strong potential for transferable representation learning, yet their adaptation in
arXiv:2605.07042v1 Announce Type: new Abstract: Large Language Model (LLM) agents are deployed in complex environments -- such as massive codebases, enterprise databases, and conversational histories
arXiv:2605.07282v1 Announce Type: new Abstract: Final outputs hide when a checkpoint commits to its next-token prediction. We introduce the convergence gap, a model-diffing diagnostic that decodes eac
arXiv:2602.02739v2 Announce Type: replace-cross Abstract: Geometric data pruning methods, while practical for leveraging pretrained models, are fundamentally unstable. Their reliance on extrinsic geom
arXiv:2605.06812v1 Announce Type: new Abstract: LLM-based agentic systems are rapidly evolving to perform complex autonomous tasks through dynamic tool invocation, stateful memory management, and mult
arXiv:2605.07593v1 Announce Type: new Abstract: Real-world audio-visual understanding requires chaining evidence that is sparse, temporally dispersed, and split across the visual and auditory streams,
arXiv:2605.06906v1 Announce Type: new Abstract: Human mobility differs from text and from generic time series in three structural ways: visits are tuple-valued events whose meaning depends on the join
Pi Studio is an extension for Pi that opens a local two-pane browser workspace for working with prompts, responses, Markdown & LaTeX documents, code files, and other common file types. It includes a l
arXiv:2605.04236v1 Announce Type: new Abstract: Large Language Model ensembles improve reasoning accuracy up to a performance boundary; beyond it, additional deliberation degrades accuracy. Static-bud
arXiv:2605.04995v1 Announce Type: new Abstract: We compare in-context learning with fixed queries and agentic learning with adaptive queries for uniform approximation of task families. We consider two
arXiv:2605.04231v1 Announce Type: new Abstract: Mirroring its ubiquity in popular media and all human activities, the use of deep learning (DL) is rapidly growing in scientific imaging modalities. How
arXiv:2605.03042v1 Announce Type: cross Abstract: This report describes ARIS (Auto-Research-in-sleep), an open-source research harness for autonomous research, including its architecture, assurance me
arXiv:2605.04556v1 Announce Type: cross Abstract: The Massive Sound Embedding Benchmark (MSEB) has emerged as a standard for evaluating the functional breadth of audio models. While initial baselines
arXiv:2605.03261v1 Announce Type: cross Abstract: Romantic breakups are among the most common and intense sources of psychological distress. We evaluated *overit*, a single-session AI chatbot that use
arXiv:2512.06393v5 Announce Type: replace-cross Abstract: Large language models (LLMs) achieve high accuracy on many reasoning benchmarks but remain brittle under structural perturbations of rule-base
arXiv:2605.03231v1 Announce Type: new Abstract: What if a browser agent could learn your work simply by watching you do it? We present cotomi Act, a browser-based computer-using agent that combines re
arXiv:2605.04458v1 Announce Type: new Abstract: Evaluation of long-form, citation-backed reports has lately received significant attention due to the wide-scale adoption of retrieval-augmented generat
arXiv:2603.13824v2 Announce Type: replace-cross Abstract: Recent advances in text-to-audio generation enable models to translate natural-language descriptions into diverse musical output. However, the
arXiv:2605.04501v1 Announce Type: new Abstract: In recent years, object detection has achieved significant progress, especially in the field of open-vocabulary object detection. Unlike traditional met
arXiv:2605.03205v1 Announce Type: cross Abstract: Large language models (LLMs) are rapidly changing how researchers in materials science and chemistry discover, organize, and act on scientific knowled
arXiv:2605.04327v1 Announce Type: new Abstract: We propose an architecture for integrating high-level, human-provided safety rules and operator-aligned semantic preferences into autonomous robot navig
arXiv:2605.04279v1 Announce Type: new Abstract: Transformer self-attention can be interpreted as a gradient flow on the unit sphere, in which tokens evolve under softmax interaction potentials and ten
arXiv:2605.04956v1 Announce Type: new Abstract: LLM-based Triton kernel generation has attracted significant interest, yet a fundamental empirical question remains unanswered: where does this capabili
arXiv:2602.04129v2 Announce Type: replace Abstract: Heterogeneous multi-robot systems are increasingly used in long-horizon missions requiring coordinated planning across diverse capabilities. However
In the high-stakes world of digital infrastructure, speed isn't just a metric — it’s currency. At Google Cloud Next ‘26 we announced the Bigtable in-memory tier, a breakthrough for our fully managed c
arXiv:2601.22725v3 Announce Type: replace Abstract: Recent advances in diffusion models have significantly elevated the visual fidelity of Virtual Try-On (VTON) systems, yet reliable evaluation remain
arXiv:2605.04075v1 Announce Type: cross Abstract: Multimodal Large Language Models face severe challenges in computational efficiency and memory consumption due to the substantial expansion of the vis
arXiv:2605.03308v1 Announce Type: new Abstract: Travel planning serves as a critical task for long-horizon reasoning, exposing significant deficits in LLMs. However, existing benchmarks and evaluation
arXiv:2601.08623v2 Announce Type: replace Abstract: Image generation models (IGMs), while capable of producing impressive and creative content, often memorize a wide range of undesirable concepts from
Stories like this is why we built E2B. Watching @genspark_ai go from zero to 250M ARR in 12 months on our infrastructure is one of the best feelings in this job. Their Super Agent does deep research,
arXiv:2602.14872v2 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has been a main driver of recent breakthroughs in large reasoning models. Yet it remains a mys
arXiv:2605.04201v1 Announce Type: new Abstract: We propose a topology-constrained quantized nnUNet framework for efficient and anatomically accurate 3D tooth segmentation, addressing the challenges of
arXiv:2605.04107v1 Announce Type: cross Abstract: Production agent frameworks (OpenAI Function Calling, Anthropic Tool Use, MCP) transmit tool schemas as JSON, a format designed for machine parsing, n