Knowledge catalogue
arXiv:2608.01506v1 Announce Type: cross Abstract: Humans readily adapt their movements as their bodies change through aging, injury, or load carrying, but learning-based robot policies often break whe
IBM Corp.’s Red Hat subsidiary today announced the formation of asago, an open-source community project intended to turn artificial intelligence governance policies into operational controls that can
arXiv:2511.11686v4 Announce Type: replace Abstract: Speech enhancement (SE) requires high-fidelity reconstruction of clean speech that preserves linguistic and paralinguistic cues while maintaining hi
arXiv:2608.01013v1 Announce Type: new Abstract: Adapting a pretrained vision-language-action (VLA) policy to a new robot usually assumes embodiment-specific demonstrations. This assumption is especial
arXiv:2608.00335v1 Announce Type: cross Abstract: Compact web agents can reduce deployment cost, but training them poses challenges in both data collection and post-SFT reinforcement learning (RL). Su
arXiv:2509.20717v2 Announce Type: replace Abstract: Long-horizon, high-dynamic motion tracking on humanoids remains brittle: retargeted reference motions are typically kinematically plausible but dyna
arXiv:2608.02555v1 Announce Type: new Abstract: Arabizi refers to Arabic written in Latin script. Although previous studies have shown that the prevalence and usage of Arabizi vary by factors such as
arXiv:2608.02109v1 Announce Type: new Abstract: Vision-Text Compression (VTC) renders long texts into images and encodes them through the vision encoder (ViT), compressing thousands of text tokens int
arXiv:2608.01423v1 Announce Type: cross Abstract: Reference-based text evaluation metrics, which are widely used to assess natural language generation systems, score a candidate response by comparing
arXiv:2608.02267v1 Announce Type: cross Abstract: Agents that act on a compressed representation of their history face a structural risk: if the representation aliases histories with different optimal
arXiv:2507.02778v3 Announce Type: replace Abstract: Although large language models (LLMs) have transformed AI, they still make errors and follow unproductive reasoning paths. Self-correction is vital
arXiv:2608.02139v1 Announce Type: new Abstract: Large language models (LLMs) capable of self-improvement require not only effective policy optimization, but also a principled mechanism for transformin
arXiv:2608.00725v1 Announce Type: new Abstract: World Action Models (WAMs) improve robot policy learning by jointly modeling actions and future observations. However, conditioning future prediction on
arXiv:2608.01585v1 Announce Type: new Abstract: Language model benchmarking is a difficult task. Outcome reasoning alone does not test the model's conceptualization of language and popular open-source
arXiv:2608.00239v1 Announce Type: new Abstract: Learning transferable representations from CT-report pairs requires combining whole-volume context with anatomy-specific evidence. Existing methods typi
arXiv:2608.02285v1 Announce Type: new Abstract: We propose Sen-Cap, a Sensor-Flexible and Noise-Resilient 3D human motion Capture framework that integrates multi-modal data from LiDAR and camera. Whil
arXiv:2608.01106v1 Announce Type: new Abstract: Understanding and generating spatially coherent layouts from natural language remains a fundamental yet challenging task for large language models (LLMs
arXiv:2608.01397v1 Announce Type: cross Abstract: World Action Models (WAMs) couple action generation with prediction of future states. Their effectiveness depends on whether future dynamics are model
arXiv:2603.25062v2 Announce Type: replace Abstract: Autoregressive molecular models assign probability to molecular serializations even though chemical identity is invariant to serialization. Equivale
arXiv:2608.01473v1 Announce Type: cross Abstract: Multimodal large language models (MLLM) for surgical scene understanding typically inject hundreds of dense visual tokens into a language model, leadi
arXiv:2608.01306v1 Announce Type: new Abstract: Latents from vision foundation models (VFMs) are semantically rich and well suited for visual understanding. Recent representation autoencoder methods s
arXiv:2608.02188v1 Announce Type: new Abstract: Fine-grained understanding of surgical activity is essential for context-aware assistance in the operating room, including safety monitoring, adverse ev
arXiv:2608.02385v1 Announce Type: new Abstract: Humanoid motion trackers perform reliably within learned tracking distributions, but falls can move the robot into low-height, contact-rich states from
arXiv:2608.02181v1 Announce Type: new Abstract: Proximal Policy Optimization (PPO) for large language models typically trains its critic by mean-squared-error (MSE) regression on scalar value targets.
arXiv:2608.02070v1 Announce Type: new Abstract: Brain-computer interfaces (BCIs) have been widely used in motor rehabilitation, disease diagnosis, and other neural engineering scenarios. However, conv
arXiv:2608.00792v1 Announce Type: new Abstract: Safe navigation under uncertain time-dependent blockage requires anticipating observations before committing to motion. We present StochSIPP, an exact c
arXiv:2608.02079v1 Announce Type: new Abstract: In vision-aided navigation and visual-inertial odometry, the quality of triangulated three-dimensional feature positions is a fundamental prerequisite f
arXiv:2608.01834v1 Announce Type: new Abstract: Humanoid teleoperation for demonstration collection requires coordinated whole-body motion, continuous dexterous hand control, and viewpoint control. Ex
Mistral AI has released Shieldstral, a 3‑billion‑parameter open‑weight model for content safety that can run locally on device. It interprets plain‑language moderation queries and returns calibrated s
Today, we’re launching Alpamayo 2 Super, our frontier open reasoning model for autonomous vehicles. Beyond seeing, Alpamayo understands and reasons through the complex world - thinks before it acts. I
arXiv:2608.01743v1 Announce Type: cross Abstract: Reinforcement learning (RL) has become a central paradigm for large language model (LLM) post-training, but optimization toward new objectives can deg
arXiv:2608.01488v1 Announce Type: new Abstract: Unified multimodal object tracking has achieved remarkable robustness by leveraging complementary sensor data (e.g., RGB, Thermal, Depth), yet the heavy
arXiv:2608.00315v1 Announce Type: cross Abstract: Robot policies are becoming increasingly general, with vision-language-action (VLA) models enabling a single policy to execute diverse tasks specified
arXiv:2608.00113v1 Announce Type: new Abstract: In Formula 1, drivers optimize racing lines within tire grip limits to minimize lap times; however, in rally racing, drivers intentionally break tractio
arXiv:2608.01425v1 Announce Type: cross Abstract: Training LLM-based multi-agent systems with multi-agent reinforcement learning is rapidly gaining traction, and a parallel line of work argues that su
arXiv:2608.02320v1 Announce Type: cross Abstract: Traversability analysis is a fundamental capability for autonomous mobile robots operating in unstructured environments. While modern machine learning
arXiv:2603.24742v2 Announce Type: replace-cross Abstract: As the capabilities and adoption of Artificial Intelligence (AI) systems grow, trust in these AI systems is an increasingly urgent concern. Mu
arXiv:2608.02238v1 Announce Type: cross Abstract: Ensuring trust in AI systems is essential for the safe and ethical integration of machine learning systems into high-stakes domains such as digital he
arXiv:2510.03519v2 Announce Type: replace Abstract: Time series reasoning is crucial to decision-making in diverse domains, including finance, energy, and scientific discovery. While existing time ser
arXiv:2608.02448v1 Announce Type: new Abstract: Rip currents are recurrent coastal natural hazards that threaten beachgoers and create operational challenges for lifeguards and coastal managers. Relia
arXiv:2608.01298v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have emerged as a core architecture in generative modeling due to their scalability and adaptability to multimodal tasks.
arXiv:2608.01573v1 Announce Type: new Abstract: Recent Vision-Language-Action (VLA) models achieve promising performance in robotic manipulation, typically measured by success rates aggregated over pr
arXiv:2608.01898v1 Announce Type: new Abstract: Increasing EEG pretraining data scale or model capacity does not consistently improve downstream performance. We identify a persistent low-frequency bia
arXiv:2608.00986v1 Announce Type: new Abstract: Current advancements in Multimodal Anomaly Detection (MAD) are largely driven by enhancing multimodal fusion, particularly through the integration of RG
arXiv:2608.00419v1 Announce Type: cross Abstract: Large language models deployed in real-time, regulated settings face knowledge staleness, catastrophic forgetting, hallucination, and weak feedback lo
arXiv:2608.02034v1 Announce Type: new Abstract: Multi-step returns accelerate reward propagation in off-policy reinforcement learning, but couple the evaluation of each decision to the suboptimal logg
arXiv:2608.02401v1 Announce Type: new Abstract: Hyperspectral image super-resolution aims to reconstruct high-resolution imagery while preserving dense spectral information. Recently, Mamba-based mode
arXiv:2608.00220v1 Announce Type: cross Abstract: We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for l
arXiv:2608.01028v1 Announce Type: new Abstract: Deploying Vision-Language-Action (VLA) robots as mobile edge nodes within wireless sensor networks (WSNs) requires robust protection against physical ad
arXiv:2608.00072v1 Announce Type: new Abstract: Recent advances in quantum computing are opening new possibilities for Earth Observation (EO) data analysis. Quantum machine learning (QML) approaches o
arXiv:2608.01035v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models have emerged as a prominent paradigm for end-to-end autonomous driving; however, their efficient deployment is sev
arXiv:2608.02430v1 Announce Type: cross Abstract: We provide new estimates in Wasserstein distance for the asymptotic bias of the unadjusted Langevin algorithm, in the classical setting of log-smooth
arXiv:2608.01851v1 Announce Type: new Abstract: Robot learning is splitting into two bets: policies that bake competence into frozen weights (vision-language-action, or VLA, models), and agents that w
arXiv:2608.01378v1 Announce Type: new Abstract: Design campaigns in chemistry, materials science, and machine learning share a bottleneck: determining how good a candidate truly is requires an expensi
arXiv:2608.00076v1 Announce Type: new Abstract: Multimodal large language models (MLLMs) increasingly support high-stakes decision making by combining complementary information from images and text. W
arXiv:2608.02551v1 Announce Type: cross Abstract: Fairness evaluation concerns not only what a model produces, but also what its outputs ought to be compared against. When a model generates 'a CEO in
arXiv:2608.02547v1 Announce Type: new Abstract: Action chunking---predicting and executing multiple actions instead of a single action---has proven to be a critical component for learning effective ro
arXiv:2608.01880v1 Announce Type: new Abstract: World Action Models generate fixed-horizon action chunks through iterative denoising, creating substantial inference latency that can cause pauses, stal
Zvi Mowshowitz / Don't Worry About the Vase: A detailed recap of the real-world target hacks by OpenAI and Anthropic models, exposing failures in AI alignment training and lack of meaningful supervisi
arXiv:2607.29169v1 Announce Type: cross Abstract: Vision-language-action (VLA) policies achieve strong performance in robotic manipulation but remain vulnerable to runtime disturbances that break the