Knowledge catalogue
arXiv:2604.17228v1 Announce Type: new Abstract: Conditional depth execution routes a subset of tokens through a lightweight cheap FFN while the remainder execute the standard full FFN at each controll
arXiv:2604.18429v1 Announce Type: new Abstract: Change visual question answering (Change VQA) addresses the problem of answering natural-language questions about semantic changes between bi-temporal r
arXiv:2511.05993v3 Announce Type: replace Abstract: Reinforcement learning with verifiable rewards (RLVR) has emerged as a prominent paradigm for enhancing the reasoning capabilities of large language
arXiv:2601.02735v2 Announce Type: replace Abstract: Decision forests induce supervised similarities through the partition structure of their trees. Yet forest proximity computation is still often trea
arXiv:2604.17415v1 Announce Type: cross Abstract: Reward-based fine-tuning aims to steer a pretrained diffusion or flow-based generative model toward higher-reward samples while remaining close to the
arXiv:2604.16683v1 Announce Type: cross Abstract: Imitation learning has enabled robots to acquire complex visuomotor manipulation skills from demonstrations, but deployment failures remain a major ob
arXiv:2604.17257v1 Announce Type: new Abstract: Recent text embedding models are often adapted to specialized domains via contrastive pre-finetuning (PFT) on a naive collection of scattered, heterogen
arXiv:2604.16821v1 Announce Type: new Abstract: Reach and Frequency (R&F) contract advertising is an important form of widely used brand advertising. Unlike performance advertising, R&F contracts emph
arXiv:2604.16384v1 Announce Type: new Abstract: We present RHINO-AR, an interactive Augmented Reality (AR) museum exhibit that reintroduces the historical mobile robot RHINO into its original exhibiti
arXiv:2604.17391v1 Announce Type: cross Abstract: RISC-V is emerging as a viable platform for automotive-grade embedded computing, with recent ISO 26262 ASIL-D certifications demonstrating readiness f
arXiv:2604.18396v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated exceptional performance across diverse domains but are increasingly constrained by high inference latency
arXiv:2602.14466v2 Announce Type: replace Abstract: With natural language generation becoming a popular use case for language models, the Bias Benchmark for Question-Answering (BBQ) has grown to be an
arXiv:2604.17341v1 Announce Type: new Abstract: Diabetic retinopathy (DR) is a leading cause of vision impairment worldwide, and automated grading systems play a crucial role in large-scale screening
arXiv:2601.15625v2 Announce Type: replace Abstract: Large language models (LLMs) can call tools effectively, yet they remain brittle in multi-turn execution: after a tool-call error, smaller models of
arXiv:2604.17134v1 Announce Type: new Abstract: We present RoIt-XMASA, a multilingual dataset that extends the Cross-lingual Multi-domain Amazon Sentiment Analysis to Italian and Romanian, comprising
arXiv:2604.16392v1 Announce Type: cross Abstract: AI in Education research increasingly relies on authentic, curriculum-grounded assessment data, yet large, well-structured exam corpora remain scarce
arXiv:2604.17175v1 Announce Type: new Abstract: We introduce RosettaSearch, an inference-time multi-objective optimization approach for protein sequence optimization. We use large language models (LLM
arXiv:2604.17301v1 Announce Type: new Abstract: Detecting harmful content in multi turn dialogue requires reasoning over the full conversational context rather than isolated utterances. However, most
Listen to the session or watch below Watch a special edition of Roundtables simulcast live from EmTech AI, MIT Technology Review’s signature conference for AI leadership. Subscribers got an exclusive
arXiv:2604.17504v1 Announce Type: new Abstract: Reinforcement learning (RL) post-training substantially improves remote sensing vision-language models (RS-VLMs). However, when handling complex remote
arXiv:2604.16993v1 Announce Type: cross Abstract: As embodied AI transitions to real-world deployment, the success of the Vision-and-Language Navigation (VLN) task tends to evolve from mere reachabili
This article discusses a collaborative approach from Vultr, Supermicro, and SUSE for deploying and managing AI workloads across cloud and edge computing environments using Kubernetes orchestration. Th
Russia eased vaccination standards when diphtheria seemed beaten. 157,000 infections. 5,000 dead. Japan dropped mandates after a trust collapse. Rubella came back. Babies born blind and deaf. Nigeria
arXiv:2604.16557v1 Announce Type: cross Abstract: Current post-training methodologies for adapting Large Vision-Language Models (LVLMs) generally fall into two paradigms: Supervised Fine-Tuning (SFT)
arXiv:2604.18512v1 Announce Type: new Abstract: Vision-Language Models (VLMs) have demonstrated remarkable progress in single-image understanding, yet effective reasoning across multiple images remain
arXiv:2604.16485v1 Announce Type: new Abstract: One of the limitations of transformer networks is the sequence length due to the quadratic nature of the attention matrix. Classical self attention uses
arXiv:2505.21722v2 Announce Type: replace Abstract: When a deep ReLU network is initialized with small weights, gradient descent (GD) is at first dominated by the saddle at the origin in parameter spa
arXiv:2604.18482v1 Announce Type: cross Abstract: Safety filters have been shown to be effective tools to ensure the safety of control systems with unsafe nominal policies. To address scalability chal
arXiv:2604.17691v1 Announce Type: new Abstract: Safety alignment in large language models is remarkably shallow: it is concentrated in the first few output tokens and reversible by fine-tuning on as f
arXiv:2604.16606v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly deployed in high-stakes domains, yet a unified treatment of their overlapping safety challenges remains
arXiv:2604.16358v1 Announce Type: cross Abstract: MLLMs are increasingly deployed in multi-turn settings, where attackers can escalate unsafe intent through the evolving visual-text history and exploi
arXiv:2604.17527v1 Announce Type: new Abstract: Safe and agile trajectory planning is essential for autonomous systems, especially during complex aerobatic maneuvers. Motivated by the recent success o
arXiv:2604.16424v1 Announce Type: cross Abstract: State-Space Models (SSMs) -- structured SSMs (S4, S4D, DSS, S5), selective SSMs (Mamba, Mamba-2), and hybrid architectures (Jamba) -- are deployed in
arXiv:2503.03480v4 Announce Type: replace Abstract: Vision-language-action models (VLAs) show potential as generalist robot policies. However, these models pose extreme safety challenges during real-w
arXiv:2601.05403v2 Announce Type: replace Abstract: Large language models (LLMs) have been widely applied across various domains of finance. Since their training data are largely derived from human-au
Same prompts as before, but now in GPT image-generator 2, page excerpts from: 'Eldritch Horrors as Pets: A Guide' 'How Womblenauts Work' 'Photographs of the People of New York Who Look Like Birds' 'Ca
arXiv:2604.16453v1 Announce Type: new Abstract: We introduce a principled probabilistic framework for reward-guided decoding in large language models, addressing the limitations of standard decoding m
arXiv:2604.16437v1 Announce Type: cross Abstract: Deep learning models for atrial fibrillation (AF) detection are increasingly trained on heterogeneous electrocardiogram (ECG) datasets with varying sa
arXiv:2604.16445v1 Announce Type: cross Abstract: Recent advances in Artificial Intelligence (AI) and the exploration of noninvasive, objective biomarkers, such as speech signals, have encouraged the
arXiv:2409.17443v2 Announce Type: replace Abstract: As space becomes increasingly crowded and contested, robust autonomous capabilities for multi-agent environments are gaining critical importance. Cu
SAUVER LA FRANCE ET L'EUROPE EN FAISANT LE SEUL PARI QUI VAILLE (série banane rouge) I. COMME BONAPARTE : CONCENTRER LES FORCES, PAS LES DILUER Dans le discours politico-industriel d'aujourd'hui, on e
arXiv:2604.16715v1 Announce Type: cross Abstract: Graph foundation models have demonstrated remarkable adaptability across diverse downstream tasks through large-scale pretraining on graphs. However,
arXiv:2604.18190v1 Announce Type: new Abstract: We propose MADDPG-K, a scalable extension to Multi-Agent Deep Deterministic Policy Gradient (MADDPG) that addresses the computational limitations of cen
arXiv:2604.18438v1 Announce Type: new Abstract: We present a scalable, data-driven simulation framework for large-scale heating, ventilation, and air conditioning (HVAC) systems that couples physics-i
arXiv:2604.16815v1 Announce Type: cross Abstract: Quantum error mitigation (QEM) provides a practical route for estimating reliable observables on noisy intermediate-scale quantum (NISQ) devices. Trad
arXiv:2604.18312v1 Announce Type: new Abstract: We address the problem of planning in an environment with deterministic dynamics and stochastic rewards with discounted returns. The optimal value funct
arXiv:2510.15253v3 Announce Type: replace Abstract: Document understanding is critical for applications from financial analysis to scientific discovery. Current approaches, whether OCR-based pipelines
OpenAI's Codex, a code generation model trained on publicly available code, was scaled for enterprise deployment to provide developers with AI-assisted coding capabilities across organizations worldwi
arXiv:2505.21471v2 Announce Type: replace Abstract: With the rapid advancement of post-training techniques for reasoning and information seeking, large language models (LLMs) can incorporate a large q
arXiv:2604.17883v1 Announce Type: cross Abstract: Vibe coding produces correct, executable code at speed, but leaves no record of the structural commitments, dependencies, or evidence behind it. Revie
arXiv:2603.24562v2 Announce Type: replace Abstract: While large-scale pretraining has revolutionized language modeling, its potential remains underexplored in healthcare with structured electronic hea
arXiv:2604.16529v1 Announce Type: cross Abstract: Test-time scaling has become a powerful way to improve large language models. However, existing methods are best suited to short, bounded outputs that
Scaling up Kimi K2.6 with more NVIDIA Blackwell GPUs! Will be adding more in the coming days. Try it with OpenClaw: ollama launch openclaw --model kimi-k2.6:cloud Try it with Hermes Agent: ollama laun
arXiv:2604.16535v1 Announce Type: new Abstract: Test-time scaling (TTS) improves large language models (LLMs) by allocating additional compute at inference time. In practice, TTS is often achieved thr
arXiv:2604.17147v1 Announce Type: new Abstract: We introduce ScenarioControl, the first vision-language control mechanism for learned driving scenario generation. Given a text prompt or an input image
arXiv:2604.17206v1 Announce Type: new Abstract: We present SciDraw-6K, a curated dataset of 6,291 scientific illustrations synthesized by Google Gemini image-generation models, each paired with prompt
arXiv:2505.19897v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) have extended their impact beyond Natural Language Processing, substantially fostering the development of interdi
arXiv:2604.17141v1 Announce Type: new Abstract: The rapid growth of scientific literature calls for automated methods to assess and predict research impact. Prior work has largely focused on citation-
arXiv:2604.17734v1 Announce Type: new Abstract: Cryo-electron microscopy (cryo-EM) enables single-particle analysis of biological macromolecules under strict low-dose imaging conditions, but the resul
scosman/pelicans_riding_bicycles I firmly approve of Steve Cosman's efforts to pollute the training set of pelicans riding bicycles. (To be fair, most of the examples I've published count as poisoning