Knowledge catalogue
arXiv:2609.25039v1 Announce Type: cross Abstract: Entropy over chain-of-thought tokens decides which tokens receive the policy gradient, which get pruned, and whether a run has collapsed, yet each suc
arXiv:2609.25638v1 Announce Type: new Abstract: Foundation vision models provide strong generic representations, yet high class-level retrieval accuracy does not necessarily imply that an embedding re
arXiv:2609.25887v1 Announce Type: new Abstract: How should a robot learn to manipulate objects so fragile that sub-Newton contact forces can cause irreversible damage? Existing visuo-tactile policy le
arXiv:2609.25623v1 Announce Type: new Abstract: More privileged information does not always make a better teacher. We study this tension in on-policy self-distillation (OPSD), where a frozen copy of t
arXiv:2609.22961v1 Announce Type: cross Abstract: Agentic systems increasingly invoke tools, services, data, and other agents across organizational boundaries, yet a relying party cannot assess a dele
arXiv:2609.24101v1 Announce Type: new Abstract: Automated biomedical evidence synthesis depends on retrieving published studies, but the biomedical literature is systematically skewed toward positive
The economics of enterprise transformation are pushing finance and human resources into much closer alignment as companies decide where artificial intelligence fits, where people create the most value
arXiv:2512.24310v4 Announce Type: replace Abstract: We introduce World In Your Hands (WIYH), a large-scale open-source ecosystem comprising over 1,000 hours of human manipulation data collected in-the
arXiv:2609.24744v1 Announce Type: new Abstract: Language agents solve complex tasks through plans and actions. A single step the world refuses puts the goal out of reach, and what the agent does next
arXiv:2609.25709v1 Announce Type: new Abstract: Environmental reconnaissance needs mobile platforms that carry sensors, preserve measurement context, and return interpretable evidence under limited en
arXiv:2609.24432v1 Announce Type: cross Abstract: Sparse on-policy distillation (OPD) allocates teacher supervision to a small subset of tokens in student-generated trajectories. However, useful teach
arXiv:2411.02455v3 Announce Type: replace Abstract: The rapid adoption of generative AI has created new opportunities for teaching, learning, and quality assurance. Existing applications, however, rem
arXiv:2407.09693v3 Announce Type: replace Abstract: The field of Neural-Symbolic (NeSy) systems is growing rapidly. Proposed approaches show great promise in achieving symbiotic unions of neural and s
arXiv:2609.24075v1 Announce Type: new Abstract: Computer-vision systems used for construction monitoring can degrade under adverse environmental and visual conditions, yet such conditions remain under
arXiv:2609.22871v1 Announce Type: new Abstract: In-hand assembly is constrained by the need to maintain grasps on two separate parts while controlling their relative motion within a single hand. To en
arXiv:2606.18193v2 Announce Type: replace-cross Abstract: We evaluate the adversarial robustness of three frontier large language models (LLMs) developed by Anthropic, Opus 4.8, Fable 5 and its succes
arXiv:2609.24127v1 Announce Type: new Abstract: Atomic activity understanding aims to recognize and localize structured traffic behaviors that jointly encode motion patterns and their grounding in roa
arXiv:2603.11984v2 Announce Type: replace Abstract: Diffusion-based visuomotor policies model complex action distributions through iterative denoising, but repeated inference adds latency to robotic c
arXiv:2606.15080v2 Announce Type: replace Abstract: While Large Reasoning Models (LRMs) show strong performance in English, they often fail to reason in the language of the query, a phenomenon known a
arXiv:2609.24109v1 Announce Type: new Abstract: Zero-shot brain-to-image retrieval requires robust alignment between noisy EEG responses and visual representations. Existing EEG-vision alignment metho
arXiv:2609.24233v1 Announce Type: new Abstract: Electroencephalography (EEG) provides non-invasive monitoring of brain activity and is widely used in emotion recognition, motor imagery and sleep stagi
arXiv:2609.24330v1 Announce Type: new Abstract: Image morphing aims to produce a smooth and semantically consistent transition between two input images. Existing diffusion-based morphing methods eithe
arXiv:2609.22942v1 Announce Type: new Abstract: Generative models are rapidly expanding image quality assessment (IQA) beyond traditional fidelity factors to emerging dimensions such as physical plaus
arXiv:2609.23097v1 Announce Type: cross Abstract: Internet of Things (IoT) systems are increasingly deployed in smart homes, transportation, energy systems, and critical infrastructure. This broad con
arXiv:2609.23048v1 Announce Type: cross Abstract: Compressed manipulation policies can pass offline evaluation while failing in closed-loop execution; this dissociation is established in prior work an
arXiv:2609.22670v1 Announce Type: new Abstract: Underwater robot simulation requires diverse environments in which terrain, scene composition, tasks, and currents remain mutually consistent. We presen
arXiv:2609.24417v1 Announce Type: new Abstract: Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are
arXiv:2609.24563v1 Announce Type: new Abstract: Adapting visuomotor policies to new manipulation tasks often requires substantial manual engineering or teleoperated data collection. Simulation can pro
arXiv:2602.04125v2 Announce Type: replace-cross Abstract: Modern digital platforms use contextual bandits to allocate valuable exposure and opportunities among competing participants. Fair treatment i
arXiv:2609.23232v1 Announce Type: cross Abstract: Bayesian graph alignment estimates correspondence probabilities, but convergence of an alignment-score trace need not imply accurate correspondence ma
arXiv:2609.22730v1 Announce Type: new Abstract: Robot manipulation tasks often involve hidden state information that cannot be directly observed and must be inferred through sequential physical intera
arXiv:2609.22633v1 Announce Type: new Abstract: Bilingual language models (LMs) offer a controlled setting for studying how training conditions shape second-language (L2) behaviour, but prior work typ
arXiv:2609.24215v1 Announce Type: new Abstract: Although text-to-image models can accurately depict subjects and scenes, creators still struggle to specify the fine-grained emotions an image should co
arXiv:2609.23445v1 Announce Type: new Abstract: Bimanual manipulation requires policies that coordinate two arms while adapting their functional roles to scene geometry, object configuration, and task
arXiv:2609.22884v1 Announce Type: new Abstract: Long-context inference has become a defining capability of large language models, but exact dense attention remains costly due to its quadratic scaling
arXiv:2506.12576v3 Announce Type: replace Abstract: Sparse autoencoders (SAEs) can enable inference-time topic steering by modifying latent feature activations, but existing steering methods often fai
arXiv:2401.08038v2 Announce Type: replace Abstract: A significant challenge to training accurate deep learning models on privacy policies is the cost and difficulty of obtaining a large and comprehens
arXiv:2609.24287v1 Announce Type: new Abstract: Classifier-free guidance (CFG) improves conditional generation in Flow Matching, but strong guidance can distort the generated distribution and reduce d
arXiv:2504.14280v2 Announce Type: replace Abstract: As machine learning evolves, domain generalization (DG) and domain adaptation (DA) have become crucial for improving model robustness across diverse
arXiv:2609.24141v1 Announce Type: new Abstract: On-policy distillation (OPD) pays twice for each fresh batch: the student generates trajectories and a stronger teacher scores them. Existing methods im
arXiv:2604.06487v2 Announce Type: replace Abstract: Conventional end-to-end automatic speech recognition (ASR) systems rely on paired speech-text data for domain adaptation. Recent LLM-based ASR archi
arXiv:2603.03768v2 Announce Type: replace Abstract: Full-stack human-robot collaboration (HRC) can become brittle when replacing a planner, partner model, coordination policy, or controller changes th
arXiv:2609.24440v1 Announce Type: new Abstract: The quadratic scaling of Transformer self-attention has driven the adoption of sub-quadratic Selective State Space Models (SSMs) like Mamba, which compr
arXiv:2609.23800v1 Announce Type: new Abstract: High-precision connector insertion remains challenging for robotic systems due to tight mechanical tolerances, partial observability during contact, and
Cool paper showing how effective tuning a system prompt for an agent can be. Recommended paper if you tune agent harnesses. This paper presents EvolveTrade, which treats a trading agent's system promp
arXiv:2609.24985v1 Announce Type: cross Abstract: Multi-turn tool-use failures can hinge on a single model call, yet reward variation alone does not reveal which call would benefit from training. When
arXiv:2609.22752v1 Announce Type: new Abstract: Diffusion models have demonstrated strong power in generative modeling tasks across multiple domains, exhibiting a remarkable capability of learning com
arXiv:2609.24877v1 Announce Type: new Abstract: In automated clinical coding, where the label space spans tens of thousands of diagnosis and procedure codes, models are currently evaluated against a s
arXiv:2609.22104v1 Announce Type: new Abstract: As automated scientific discovery advances, Large Language Models (LLMs) can now generate research ideas at an unprecedented scale, shifting the bottlen
arXiv:2609.24093v1 Announce Type: new Abstract: Learning dexterous manipulation from demonstrations is bottlenecked by data: the contact forces that determine whether a grasp succeeds are absent from
arXiv:2609.24223v1 Announce Type: new Abstract: Dynamic Time Warping (DTW) is the dominant approach for measuring similarity between time series, yet standard practice discards the optimal warping pat
arXiv:2609.22256v1 Announce Type: new Abstract: Effective workplace negotiation requires balancing multiple objectives, including achieving task goals, preserving professional relationships, and resol
arXiv:2507.22920v2 Announce Type: replace Abstract: The rapid advancement of large language models (LLMs) has intensified the need for effective mechanisms to transform continuous multimodal data into
arXiv:2609.23697v1 Announce Type: new Abstract: Multi-teacher on-policy distillation allows a student to learn from complementary specialists on its own trajectories. Domain-routed approaches, however
arXiv:2609.22706v1 Announce Type: new Abstract: Identity association in multi-object tracking (MOT) is vulnerable to partial occlusion, truncated detections, and fluctuating confidence scores. Existin
arXiv:2609.24872v1 Announce Type: new Abstract: Two-stage oriented detectors achieve high localization accuracy in synthetic aperture radar (SAR) ship detection, but their large backbones, feature pyr
arXiv:2504.11809v2 Announce Type: replace Abstract: Simultaneous speech translation (SimulST) produces translations incrementally while processing partial speech input. Although large language models
arXiv:2609.22319v1 Announce Type: new Abstract: The rapid progress of artificial intelligence is reshaping robotics and accelerating the adoption of learning-based approaches. While purely data-driven
arXiv:2609.22926v1 Announce Type: new Abstract: Reach-and-attach of soft robotic arms with passive suction requires accurate targeting and sufficient contact speed, yet geared actuators can impose a s
Especially compared by per-task pricing, which is the metric that should matter, I don't think there is anything competitive anywhere in the market. We want people to be able to use tons of AI; it is