All entries

arXiv:2605.10853v1 Announce Type: new Abstract: Humor generation remains challenging task for Large Language Models (LLMs), due to their subjective nature. We focus on satire, a form of humor strongly

arXiv:2603.16253v2 Announce Type: replace-cross Abstract: Vision-language process reward models (VL-PRMs) are increasingly used to score intermediate reasoning steps and rerank candidates under test-t

arXiv:2605.09619v1 Announce Type: new Abstract: Accurate High-Definition (HD) map construction is critical for autonomous driving, yet existing methods face a fundamental trade-off: vectorization-base

arXiv:2605.10582v1 Announce Type: cross Abstract: This paper proposes a guaranteed defense method for large language models (LLMs) to safeguard against jailbreaking attacks. Drawing inspiration from t

arXiv:2508.20325v3 Announce Type: replace-cross Abstract: As Large Language Models (LLMs) become increasingly integral to various domains, their potential to generate harmful responses has prompted si

arXiv:2605.10386v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) are increasingly integrated into autonomous driving (AD) systems; however, they remain vulnerable to diverse sa

arXiv:2605.10051v1 Announce Type: cross Abstract: Inference-time guidance is essential for steering generative robot policies toward dynamic objectives without retraining, yet existing methods are lar

arXiv:2411.04077v2 Announce Type: replace Abstract: By leveraging both texts and images, large vision language models (LVLMs) have shown significant progress in various multi-modal tasks. Nevertheless

Had an interesting exchange with roon of OpenAI last night over whether super intelligent AI would actually be able to navigate organizational challenges. @tszzl I think it is a reasonable argument to

arXiv:2605.09942v1 Announce Type: new Abstract: Memory retrieval in agentic large language model (LLM) systems is often treated as a static lookup problem, relying on flat vector search or fixed binar

arXiv:2605.08824v1 Announce Type: cross Abstract: Hair is a rich medium of visual and cultural expression, yet its digital modeling remains challenging due to the duality of fluidity and structure. Ma

arXiv:2605.10374v1 Announce Type: new Abstract: Underwater images captured by Autonomous Underwater Vehicles (AUVs) are inevitably affected by artificial light sources, which often produce halos in th

arXiv:2110.12907v2 Announce Type: replace-cross Abstract: Existing rigorous convergence guarantees for the Hamiltonian Monte Carlo (HMC) algorithm use Gaussian auxiliary momentum variables, which are

arXiv:2507.15518v5 Announce Type: replace Abstract: Creating an immersive and interactive theatrical experience is a long-term goal in the field of interactive narrative. The emergence of large langua

Happy One Year Anniversary, AGI!* What an amazing, hallucination-free year it has been!* Glad we can totally trust you now!* *I was being sarcastic. @codeslubber tyler cowen literally said o3 was AGI.

arXiv:2605.09971v1 Announce Type: cross Abstract: Text-to-vibration generation converts natural language into haptic feedback, enabling vibration-effect designers to get scenarios-fitted vibrations mo

arXiv:2605.08210v1 Announce Type: new Abstract: Multi-rater medical image segmentation captures the inherent ambiguity of clinical interpretation, where diagnostic boundaries vary across experts and i

arXiv:2605.10942v1 Announce Type: new Abstract: World Action Models (WAMs) have emerged as a promising paradigm for robot control by modeling physical dynamics. Current WAMs generally follow two parad

Monica Hunter-Hart / Forbes: Havoc, which offers autonomous boats and software to control thousands of vessels at once, raised a 100M Series A led by Cobalt and Boardman Bay — Interest in drone boats

arXiv:2605.08456v1 Announce Type: cross Abstract: The realtime analysis and secure transmission of electrocardiogram ECG signals are critical for accurate diagnosis and safeguarding patient privacy in

arXiv:2509.23668v3 Announce Type: replace Abstract: Time series forecasting occurs in a range of financial applications providing essential decision-making support to investors, regulatory institution

arXiv:2605.10201v1 Announce Type: cross Abstract: Generalizable manipulation involving cross-type object interactions is a critical yet challenging capability in robotics. To reliably accomplish such

arXiv:2605.10717v1 Announce Type: cross Abstract: Multi-agent trajectory modeling traditionally focuses on forecasting, often neglecting more general tasks like trajectory completion, which is essenti

arXiv:2605.10536v1 Announce Type: cross Abstract: Rare semantic innovations in high-dimensional, mission-critical domains are often obscured by dense background contexts, a challenge we define as exti

arXiv:2605.09502v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting assumes that generated reasoning reflects a model's internal computation. We show this assumption is wrong in a speci

arXiv:2602.01442v3 Announce Type: replace-cross Abstract: Gradient-based attribution is the workhorse of mechanistic interpretability, yet whether it reliably tracks causal importance at the component

arXiv:2605.09972v1 Announce Type: cross Abstract: End-to-end autonomous driving has witnessed rapid progress, yet existing benchmarks are increasingly saturated, with state-of-the-art models achieving

arXiv:2605.09308v1 Announce Type: cross Abstract: Graph Neural Networks (GNNs) excel at relational reasoning but face two persistent challenges: the lack of interpretable attribution for heterogeneous

arXiv:2605.10624v1 Announce Type: new Abstract: Model Predictive Control (MPC) is widely used to operate safety-critical infrastructure by predicting future trajectories and optimizing control actions

arXiv:2605.10621v1 Announce Type: new Abstract: Reachability analysis of neural networks, which seeks to compute or bound the set of outputs attainable over a given input domain, is central to certify

arXiv:2605.08292v1 Announce Type: cross Abstract: Sparse Mixture-of-Experts (MoE) models scale capacity by routing each token to a small subset of experts. However, their routers exhibit a fundamental

arXiv:2605.08232v1 Announce Type: new Abstract: High-fidelity experimental characterization of turbulent premixed flames remains limited by the cost and complexity of advanced diagnostics, particularl

arXiv:2605.08330v1 Announce Type: new Abstract: We present a hierarchical language-driven framework for robotic task and motion planning to improve natural, intuitive human-robot interaction in servic

arXiv:2410.14927v2 Announce Type: replace-cross Abstract: Automated equity trading requires converting noisy market and news signals into executable portfolio decisions under risk, turnover, and trans

arXiv:2512.21815v2 Announce Type: replace Abstract: Vision-language models (VLMs) achieve remarkable performance but remain vulnerable to adversarial attacks. Entropy, as a measure of model uncertaint

arXiv:2605.09465v1 Announce Type: new Abstract: High-precision heavy-duty grading is a common step in earthworks, traditionally carried out manually by skilled operators. Removing a significant amount

arXiv:2509.21484v3 Announce Type: replace Abstract: We study online convex optimisation with ell_q-Lipschitz losses, ell_p-regularised FTRL, and randomised two-point finite-difference gradient estimat

arXiv:2605.08864v1 Announce Type: new Abstract: We study online estimation in latent-variable models by recasting the problem as tracking a moving empirical equilibrium. Standard online EM and stochas

arXiv:2605.10546v1 Announce Type: new Abstract: Pixel-based deep reinforcement learning agents are typically trained on heavily downsampled visual observations, a convention inherited from early bench

Highlights: 👉 600+ voices across MiniMax, Cartesia, Deepgram, Rime, and more 👉 Search by prompt or audio sample 👉 Filter by 15+ attributes, including pitch, accent, language, age, emotion, and speakin

arXiv:2605.08665v1 Announce Type: new Abstract: Large reasoning models achieve high accuracy through extended chain-of-thought but generate 5--8 more tokens than necessary, applying verbose reasoning

arXiv:2602.09524v3 Announce Type: replace Abstract: Unsupervised industrial anomaly detection (UAD) is essential for modern manufacturing inspection, where defect samples are scarce and reliable detec

arXiv:2404.18923v5 Announce Type: replace Abstract: We introduce Holmes, a new benchmark designed to assess language models (LMs) linguistic competence - their unconscious understanding of linguistic

arXiv:2605.09348v1 Announce Type: cross Abstract: Large Language Models (LLMs) provide flexible natural language processing capabilities, while knowledge graphs (KGs) offer explicit and structured kno

Full-stack observability startup Hound Technology Inc., which does business as Honeycomb, introduced a number of new platform updates aimed at investigating artificial intelligence agent activity in p

arXiv:2605.08143v1 Announce Type: cross Abstract: Large language models encode vast factual knowledge that inevitably becomes outdated or incorrect after deployment, yet retraining is costly prohibiti