Knowledge catalogue
arXiv:2609.40153v1 Announce Type: new Abstract: Video generation models (VGMs) offer strong spatiotemporal priors for embodied observation--action modeling. However, joint-space action vectors lack ex
arXiv:2609.39710v1 Announce Type: new Abstract: Scientific abstracts mix contributions with background, motivation, and meta-language, so tools that read them as-is cannot separate what a field produc
arXiv:2609.38948v1 Announce Type: cross Abstract: Frontier models excel at many digital benchmarks, yet their ability to drive a real car, an everyday human skill, remains largely untested. We present
arXiv:2609.38588v1 Announce Type: new Abstract: Although multicopter drones are traditionally designed for 'perception-only' tasks, like mapping and exploration, recent work has sought to develop Unma
arXiv:2609.39198v1 Announce Type: new Abstract: While Vision-Language-Action (VLA) models excel in static tasks, they struggle in dynamic environments where objects are in motion (e.g., conveyor belt
arXiv:2609.38197v1 Announce Type: cross Abstract: Financial time-series forecasting must capture price dynamics across heterogeneous assets while incorporating news available at prediction time. We in
arXiv:2609.39446v1 Announce Type: new Abstract: Existing full-duplex speech benchmarks cover only subsets of real-time interaction behaviors, often under limited contextual conditions. We introduce Du
arXiv:2605.21603v1 Announce Type: cross Abstract: Intra-device parallelism addresses resource under-utilization in ML inference and training by overlapping the execution of operators with different re
arXiv:2609.40306v1 Announce Type: cross Abstract: Pretrained robot policies provide useful action priors, but long-horizon manipulation still requires coordination between semantic reasoning and physi
arXiv:2609.39839v1 Announce Type: new Abstract: Class-Incremental Learning (CIL) aims to continuously learn new classes without forgetting previously acquired knowledge. Parameter-efficient fine-tunin
arXiv:2601.21857v2 Announce Type: replace Abstract: We revisit diffusion-based generation for structured visual content and identify a fundamental limitation of existing approaches: foreground preserv
arXiv:2609.39190v1 Announce Type: new Abstract: A deep classifier is defined not only by the decision it produces, but also by the sequence of transformations through which that decision is formed. Tr
arXiv:2609.39841v1 Announce Type: new Abstract: Reconstructing dynamic driving scenes from recorded sensor data supports closed-loop evaluation of autonomous driving systems by synthesizing observatio
arXiv:2609.38335v1 Announce Type: cross Abstract: Coding agents powered by large language models (LLMs) are evolving from making localized code changes to developing complete software repositories. Ho
arXiv:2609.39575v1 Announce Type: cross Abstract: Generating full-body co-speech motion for humanoid robots requires coordinating speech prosody, linguistic content, and embodiment-specific motion. To
arXiv:2511.10333v2 Announce Type: replace-cross Abstract: Training large language models (LLMs) at scale incurs substantial communication overhead, while static gradient compression cannot adapt to gr
arXiv:2609.39259v1 Announce Type: new Abstract: Modern neural networks scale predictably, yet the mechanisms behind these regularities remain unclear. Neural redundancy is typically characterized by c
arXiv:2509.18349v4 Announce Type: replace-cross Abstract: Meta-learning aims to leverage information across related tasks to improve prediction on unlabeled data for new tasks when only a small number
arXiv:2609.39553v1 Announce Type: new Abstract: 3D Gaussian Splatting (3DGS) enables real-time novel view synthesis, but existing general-purpose acceleration methods suffer severe rendering quality d
arXiv:2609.40034v1 Announce Type: cross Abstract: Over the past decade, Machine Learning (ML) has been trained under dual objectives: minimizing prediction error via Empirical Risk Minimization (ERM)
arXiv:2609.40093v1 Announce Type: cross Abstract: Expert parallelism (EP) enables inference of large Mixture-of-Experts (MoE) models by placing their experts across multiple GPUs, but requires substan
arXiv:2609.38862v1 Announce Type: cross Abstract: Safe and efficient trajectory planning is essential in autonomous driving. However, existing end-to-end approaches often fall short in both computatio
arXiv:2609.38932v1 Announce Type: new Abstract: Surface electromyography (sEMG) provides a wearable, camera-free signal for continuous hand-motion inference. Mapping muscle activity to joint kinematic
arXiv:2609.40341v1 Announce Type: cross Abstract: Egocentric human data provides a scalable source of experience for robot learning, but varies substantially in human-robot alignment, behavioral cover
arXiv:2609.39378v1 Announce Type: new Abstract: Real-world embodied tasks, from everyday activities to professional procedures, require agents to act under physical constraints while tracking evolving
arXiv:2609.39371v1 Announce Type: new Abstract: In hospital workflows, electronic health records (EHRs) are often noisy, and may not contain the evidence needed to confirm events or measurements refer
arXiv:2609.38193v1 Announce Type: cross Abstract: Patient world models and clinical agents aim to predict changes in patients' health and support clinical work. Developing these systems requires relia
arXiv:2606.12420v2 Announce Type: replace-cross Abstract: Our concepts of survival and self-interest were built for single, continuous biological lives. These ideas break down when applied to artifici
arXiv:2609.39340v1 Announce Type: new Abstract: Electrolyte formulation design requires balancing multiple physicochemical properties, yet existing models often focus on a limited subset. Learning eac
arXiv:2609.38182v1 Announce Type: cross Abstract: Avatar-based multimodal empathetic response generation has emerged as a pivotal capability in human-centric systems, aiming to recognize user emotions
arXiv:2512.06174v3 Announce Type: replace Abstract: Generating realistic cast shadows for inserted foreground objects requires reasoning about scene geometry and illumination. However, most learning-b
arXiv:2609.38437v1 Announce Type: new Abstract: Teleoperation systems are tuned for channel fidelity, while whether the operator experiences the device as part of the body, the Sense of Embodiment (So
arXiv:2609.38905v1 Announce Type: new Abstract: Adapting robot manipulation policies to new tasks and environments remains highly data-intensive, while the data needed for further improvement depends
arXiv:2609.39227v1 Announce Type: cross Abstract: Over a century ago, Henri Poincare argued that a motionless observer cannot acquire the notion of space. Yet, most visual representation learning meth
arXiv:2609.39284v1 Announce Type: cross Abstract: While large language models have achieved remarkable success in isolated code generation, authentic software engineering requires sustained reasoning,
arXiv:2609.40037v1 Announce Type: new Abstract: Few-step autoregressive video generation enables efficient streaming synthesis, but errors introduced in early temporal blocks are reused as context and
arXiv:2609.38689v1 Announce Type: new Abstract: Immersive displays can enable rich and diverse virtual experiences. Manually authoring every possible experience to realize this potential, however, is
arXiv:2609.39829v1 Announce Type: cross Abstract: Modern machine learning depends heavily on massive datasets, but obtaining high-quality annotations at scale is often expensive. As a result, learning
arXiv:2307.15494v3 Announce Type: replace-cross Abstract: Hindsight Experience Replay (HER) enhances sample efficiency in goal-conditioned reinforcement learning (RL) by relabelling failed trajectorie
arXiv:2609.38622v1 Announce Type: new Abstract: Reconstructing and animating water scenery from nature produces compelling and immersive visual experiences. Previous work examined this task from the p
arXiv:2603.01209v3 Announce Type: replace Abstract: In CodeAct, language-model agents write Python that calls tools and use execution feedback to choose actions. Persistent runtimes preserve Python va
arXiv:2609.38357v1 Announce Type: new Abstract: Conversational safety evaluations often test language models with a single harmful prompt, even though real-world systems interact with users through lo
arXiv:2609.38271v1 Announce Type: new Abstract: Morphological characteristics such as spiculation and lobulation play an important role in assessing pulmonary nodules on computed tomography (CT), part
arXiv:2609.38797v1 Announce Type: cross Abstract: As AI systems move from static repositories to agents that are capable of continual adaptation and learning, maintaining their trustworthiness means e
arXiv:2609.38415v1 Announce Type: cross Abstract: This technical report presents an alignment evaluation developed and performed by the UK AI Security Institute for assessing whether advanced AI syste
arXiv:2609.38406v1 Announce Type: new Abstract: Access to real-world information is often noisy and fragmented. Constructing a coherent narrative from such fragments requires models to reconstruct mis
arXiv:2609.38758v1 Announce Type: new Abstract: Referring Video Object Segmentation (RVOS) aims to produce a pixel-accurate mask sequence for an object specified by natural language. Sa2VA combines a
arXiv:2609.39013v1 Announce Type: new Abstract: EVICALC, our system for the DocSem shared task, achieved 8.61% joint accuracy on 1,730 tasks in the official final test evaluation. It reads a PDF, sele
arXiv:2609.40230v1 Announce Type: cross Abstract: Visual perception is conventionally formulated as a one-shot prediction from a single glance at the image, under the assumption that the image content
arXiv:2609.40340v1 Announce Type: new Abstract: Evolutionary search with large language models (LLMs) can stall when progress requires external knowledge the model lacks. Supplying relevant documents
arXiv:2603.17343v3 Announce Type: replace Abstract: The rapid proliferation of AI-Generated Images (AIGIs) poses severe misinformation risks, making AIGI detection critical yet challenging. Traditiona
arXiv:2609.38334v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed as agents for multi-step decision-making, yet transfer poorly to unseen environments. World-model
arXiv:2609.38661v1 Announce Type: new Abstract: In recent years, LLM-based multi-agent systems have been widely applied to orchestrate tool-using agents into executable communication graphs. However,
arXiv:2609.39973v1 Announce Type: new Abstract: Vision-language-action (VLA) policies emphasize semantic understanding, whereas world-action models (WAMs) learn predictive representations of environme
Behavior intelligence company Exabeam Inc. today introduced a batch of new artificial intelligence features that push its cloud-based New-Scale platform further into agent-driven investigations. The c
arXiv:2609.38346v1 Announce Type: new Abstract: When a student is stuck, a tutor faces the assistance dilemma: help given too early can hinder productive struggle, while help withheld too long leaves
Excited to share that I have joined @MistralAI, where I will be building a team in Montreal and across Canada to push the frontier of safe, capable, and open LLMs. Mistral has played, and will continu
arXiv:2606.13571v2 Announce Type: replace-cross Abstract: Real-world time series are often highly incomplete and irregular due to sensor dormancy, transmission delays, and event-driven sampling, makin
arXiv:2609.38615v1 Announce Type: cross Abstract: Egocentric videos of human manipulation provide valuable visual experience for embodied intelligence, yet collecting such data at scale is costly. Exo
arXiv:2609.39624v1 Announce Type: new Abstract: Single-image HDR reconstruction requires inferring missing detail while preserving the visible content of an LDR image. Differences in sensor dynamic ra