Knowledge catalogue
arXiv:2609.22879v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have emerged as a powerful paradigm for embodied intelligence, but fine-tuning them with reinforcement learning (RL)
arXiv:2609.23769v1 Announce Type: new Abstract: The disambiguation of semantically similar statutory text across jurisdictions is a retrieval problem that existing methods do not solve. This inter-con
arXiv:2609.23144v1 Announce Type: new Abstract: 3D scene graphs provide semantically rich and hierarchical representations for robot perception. However, existing systems do not maintain uncertainty a
arXiv:2609.23845v1 Announce Type: new Abstract: Decentralised federated learning removes the aggregation server but makes collaboration dependent on transient peer availability. In mobile and intermit
arXiv:2609.22733v1 Announce Type: new Abstract: This paper develops the Rapidly-iterating kinoDynamic Grid (RDG) algorithm, an asymptotically near-optimal kinodynamic motion planning algorithm that pr
arXiv:2609.23439v1 Announce Type: new Abstract: Non-prehensile manipulation is practical for relocating large, heavy, or geometrically ungraspable objects. Yet, long-horizon pushing of arbitrarily-sha
arXiv:2406.03678v2 Announce Type: replace Abstract: On-policy reinforcement learning methods, like Trust Region Policy Optimization (TRPO) and Proximal Policy Optimization (PPO), often demand extensiv
arXiv:2609.24103v1 Announce Type: new Abstract: In many real-world planning tasks, agents must tackle uncertainty about the environment's state and variability in the outcomes of any chosen policy. We
arXiv:2602.09300v2 Announce Type: replace Abstract: We consider the policy evaluation and control in a finite horizon reinforcement learning (RL) setting under an expectile-based objective. First, we
arXiv:2609.24727v1 Announce Type: new Abstract: Spatial--temporal benchmarks are valid only when their questions, source annotations, and answer options identify the same physical quantity. We audit S
arXiv:2609.22988v1 Announce Type: new Abstract: Multilingual code language models transfer skills across programming languages (PLs), but whether any PL occupies a privileged pivot position remains co
arXiv:2609.23910v1 Announce Type: new Abstract: Simulation-based evaluation provides a scalable and repeatable alternative to real-world evaluation of vision-language-action (VLA) policies. However, r
arXiv:2609.22678v1 Announce Type: cross Abstract: Density-Driven Optimal Control (D2OC) provides an effective framework for steering multi-agent systems toward prescribed spatial distributions. Howeve
arXiv:2609.23457v1 Announce Type: new Abstract: Reinforcement Learning with Verifiable Rewards (RLVR) is expanding from tasks with well-defined correctness signals, such as mathematics and code, towar
arXiv:2609.23252v1 Announce Type: cross Abstract: A robot policy is trained with one of two action parameterizations: absolute joint targets, or deltas relative to the current state. The choice is a l
arXiv:2609.22785v1 Announce Type: new Abstract: Market-making strategies in real limit order book markets face substantial model uncertainty and regime-shift risk. Existing adversarial reinforcement l
arXiv:2609.23427v1 Announce Type: new Abstract: Vision foundation models targeting Earth observation (EO) tasks are commonly evaluated on clean downstream benchmarks, but operational EO products can a
arXiv:2609.24304v1 Announce Type: cross Abstract: Astronomical maps made with different tracers are not expected to have identical morphology. Excitation, optical depth, chemistry, radiation, and ISM
arXiv:2603.18532v3 Announce Type: replace-cross Abstract: The strong performance of large vision-language models (VLMs) trained with reinforcement learning (RL) has motivated similar approaches for fi
arXiv:2609.23275v1 Announce Type: new Abstract: Vision-language-action (VLA) policies increasingly incorporate structured intermediate supervision beyond action labels. Yet specifying what an intermed
arXiv:2606.13279v2 Announce Type: replace Abstract: In bimanual robotic manipulation, task-relevant visual information varies with the task stage and context, while the interaction of the two arms shi
arXiv:2609.23131v1 Announce Type: new Abstract: Language-guided object retrieval under partial observability requires deciding whether to gather more evidence, interact with the scene, grasp a candida
arXiv:2602.24208v2 Announce Type: replace Abstract: Diffusion models achieve state-of-the-art video generation quality, but their inference remains expensive due to the large number of sequential deno
arXiv:2609.23305v1 Announce Type: new Abstract: Manipulation under time constraints requires both accurate actions and an execution rhythm that matches the evolving scene. This becomes critical when a
Our most recent work at Templar explores fault tolerance in Crucible, our distributed pre-training platform. The goal is to keep healthy workers training when another pipeline stage goes offline. Cruc
arXiv:2609.22630v1 Announce Type: new Abstract: Subjective user experience is important to human-robot interaction, but the outcomes users value, and how those preferences vary across individuals and
arXiv:2603.14598v2 Announce Type: replace Abstract: Microgravity rendezvous and close proximity operations (RPO) is a growing area of interest for applications spanning in-space assembly and manufactu
arXiv:2609.24552v1 Announce Type: new Abstract: Embodied AI systems, particularly humanoid robots deployed in real world scenarios require whole-body control policies that are both task-responsive and
arXiv:2609.23955v1 Announce Type: new Abstract: Previous work on Egyptian Arabic in NLP has focused largely on the prestigious Cairene Egyptian Arabic (CEA) dialect, resulting in a lack of representat
arXiv:2609.23248v1 Announce Type: new Abstract: A fundamental challenge in deploying vision models is domain shift, which arises when training and test data follow different distributions, leading to
arXiv:2609.23643v1 Announce Type: new Abstract: Autonomous navigation of unmanned aerial vehicles in constrained three-dimensional environments has been a challenge in the robotics domain. The applica
arXiv:2609.22888v1 Announce Type: new Abstract: Online post-training of vision-language-action (VLA) models requires efficient use of robot interaction and reliable policy improvement from continually
arXiv:2609.24187v1 Announce Type: cross Abstract: Autonomous endoscopic navigation requires the policy model to predict actions from texture-poor monocular observations, make safe control decisions, a
arXiv:2609.22534v1 Announce Type: cross Abstract: Strategic classification studies how a decision maker should choose a classifier when the agents being classified can adjust their features in respons
arXiv:2609.23483v1 Announce Type: new Abstract: Humanoid loco-manipulation faces two prominent limitations: controllers using continuous velocity commands cannot precisely regulate individual foothold
arXiv:2609.22094v1 Announce Type: new Abstract: Content moderation systems traditionally entangle multimodal understanding with policy-specific classification, requiring full pipeline retraining for e
arXiv:2609.24303v1 Announce Type: cross Abstract: Post-training often improves task performance but can degrade confidence calibration, leaving post-trained language models (PoLMs) more overconfident
arXiv:2609.24156v1 Announce Type: new Abstract: Most existing time series forecasting methods rely solely on numerical observations, overlooking rich contextual information from auxiliary texts. Recen
arXiv:2609.24385v1 Announce Type: new Abstract: Tactile sensing is an essential modality for robots performing contact-rich, dexterous manipulation, particularly under visual occlusion. While pre-trai
arXiv:2609.23151v1 Announce Type: cross Abstract: Assembly remains a challenging robotic manipulation task in presence of tight tolerances and complex contact interactions. While Learning from Demonst
arXiv:2609.22254v1 Announce Type: new Abstract: On-policy distillation (OPD) is a promising approach for transferring knowledge between language models, where a student receives dense token-level supe
arXiv:2609.22850v1 Announce Type: new Abstract: Contrastive activation directions are often interpreted from what they decode or how strongly they steer behavior. But what evidence is sufficient to id
arXiv:2609.24821v1 Announce Type: new Abstract: The Linear Representation Hypothesis associates high-level concepts with directions in language models, but it remains unclear how these concept-related
arXiv:2609.22214v1 Announce Type: new Abstract: Long multilingual conversational spoken question answering requires systems to balance long-range transcript semantics with sparse acoustic and speaker-
arXiv:2609.24885v1 Announce Type: new Abstract: When a language model answers from a curated corpus via graph-based retrieval, a large grounding uplift does not establish reasoning over the retrieved
arXiv:2609.23374v1 Announce Type: new Abstract: Reinforcement learning (RL) offers a natural language for healthcare decisions whose conse- quences unfold over time, yet most reported progress remains
The longer the AI psychodrama goes on, the more it’s clear we are dealing with a conventional business bubble. What’s different this time is the lengths to which the companies will go to put off the r
arXiv:2609.24682v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models map observations to actions with no objective that accounts for how the world responds, so their robustness is bou
arXiv:2609.24660v1 Announce Type: new Abstract: Human demonstrations offer a scalable way to collect manipulation data, but their contacts may be unstable or infeasible when transferred to a robot han
arXiv:2609.22113v1 Announce Type: new Abstract: Persistent low retention and completion rates in medications for opioid use disorder (MOUD) have driven the use of machine learning (ML) models to predi
arXiv:2406.03894v2 Announce Type: replace Abstract: Proximal Policy Optimization (PPO) is a popular model-free reinforcement learning algorithm, esteemed for its simplicity and efficacy. However, due
arXiv:2609.22098v1 Announce Type: new Abstract: Speculative decoding accelerates language-model inference by letting a cheap drafter propose tokens that the target model verifies in parallel. Recent b
arXiv:2609.23666v1 Announce Type: new Abstract: Open-world deployment requires humanoid robots to cross highly heterogeneous terrain safely, with perception that simultaneously provides wide coverage,
arXiv:2506.08641v3 Announce Type: replace-cross Abstract: Adapting vision models for time series analysis is compelling, yet all existing approaches are falling short of dedicated time series foundati
arXiv:2609.24815v1 Announce Type: new Abstract: Scalable simulation is essential for robot data generation, policy training, evaluation, and safe iteration, yet real-world interaction is costly and co
arXiv:2609.23118v1 Announce Type: new Abstract: Reinforcement learning for off-road navigation requires extensive vehicle-terrain interaction data, which are costly to collect in high-fidelity simulat
arXiv:2609.23817v1 Announce Type: new Abstract: We present VISTA, a two-stage framework for generating stylized 3D human motion by fusing structural content from text prompts with expressive style fro
arXiv:2609.24906v1 Announce Type: new Abstract: Dormant tree pruning is labor-intensive yet essential for maintaining modern high-productivity fruit orchards. In this work, we focus on pruning of mode
arXiv:2609.24274v1 Announce Type: new Abstract: Deploying language-conditioned manipulation without a dedicated GPU requires efficient inference and action chunks that cover the delay between policy q
arXiv:2609.24485v1 Announce Type: new Abstract: Visual token pruning is a promising approach to reducing the inference cost of large vision-language models (LVLMs), yet aggressive token reduction ofte