Knowledge catalogue
arXiv:2610.17572v1 Announce Type: new Abstract: While expert demonstrations on real robots are difficult to collect, human ego-centric videos are easy to collect and abundant on the internet. However,
arXiv:2610.18872v1 Announce Type: cross Abstract: Learning humanoid loco-manipulation from human demonstrations rests on observing how locomotion, posture, and object interaction evolve together as ta
arXiv:2610.18822v1 Announce Type: new Abstract: Egocentric human videos offer a scalable alternative to robot teleoperation for collecting dexterous manipulation data. However, two challenges limit th
arXiv:2610.18499v1 Announce Type: new Abstract: Egocentric video understanding spans diverse capabilities, modalities, and evaluation formats, yet these are often studied in isolation despite their ti
arXiv:2610.17128v1 Announce Type: new Abstract: Egocentric video provides a continuous first-person record of everyday activities, making it a natural foundation for wearable AI assistants. Unlike off
arXiv:2610.16256v1 Announce Type: new Abstract: Head-mounted body and bimanual motion capture supports self-avatars, teleoperation, and embodied demonstrations. However, a single egocentric camera is
arXiv:2610.15555v1 Announce Type: new Abstract: Training-free story visualization without reference images must preserve recurring entities across frames while scaling to long narratives. Existing met
arXiv:2610.16118v1 Announce Type: new Abstract: Hour-long videos, streaming feeds, and movie-length content are pushing vision-language models (VLMs) past their breaking point -- the standard recipe o
arXiv:2610.15580v1 Announce Type: new Abstract: This paper presents an algorithm for detecting and fitting multiple ellipsoids in 2D, 3D and higher-dimensional data. The representation is based on tan
arXiv:2512.01495v3 Announce Type: replace Abstract: Video instance segmentation (VIS) for low-light content remains highly challenging for both humans and machines alike, due to noise, blur and other
arXiv:2610.14214v1 Announce Type: new Abstract: Hallucination detection is critical for ensuring the reliability of Large Language Models (LLMs) in real-world deployments. While recent works, such as
arXiv:2610.16238v1 Announce Type: new Abstract: LLM agents increasingly control robots using VLA policies, perception models, and procedural knowledge. These modules are difficult to reuse because the
arXiv:2610.14106v1 Announce Type: new Abstract: Large language models can translate natural-language instructions into plausible manipulation plans, but robotic execution requires physically grounded
arXiv:2610.18867v1 Announce Type: new Abstract: Bringing general-purpose agents into the physical world calls for an executable representation of physical intelligence. Compared with vision-language-a
arXiv:2610.15274v1 Announce Type: new Abstract: Training humanoid robots to learn human behaviors requires expensive data collection, and human-robot interaction data can be even more difficult and co
arXiv:2606.12965v2 Announce Type: replace Abstract: Scalable robot imitation learning relies on large-scale heterogeneous data from diverse robots or body-free data, making Cartesian end-effector acti
arXiv:2610.18742v1 Announce Type: cross Abstract: Gauge-equivariant graph neural networks generate ordered products of gauge links through local message passing, but the geometry of these internal str
arXiv:2610.18455v1 Announce Type: new Abstract: Rapid advances in artificial intelligence-generated content (AIGC) have significantly promoted using text-to-image (T2I) models to generate images with
arXiv:2610.15452v1 Announce Type: new Abstract: Text-to-video (T2V) models are increasingly used to generate videos with targeted emotional expressions, yet existing evaluation methods mainly rely on
arXiv:2610.18738v1 Announce Type: new Abstract: Off-policy data in reinforcement learning with verifiable rewards (RLVR) can arise from asynchronous generation, rollout-training mismatch, and response
arXiv:2610.14977v1 Announce Type: new Abstract: Embodied agents built on foundation models rely on an execution harness to organize observations, guide actions, and incorporate execution feedback into
arXiv:2610.17686v1 Announce Type: cross Abstract: Longer contexts allow large language models (LLMs) to condition their predictions on more information, but inference costs grow prohibitively with con
arXiv:2506.18532v2 Announce Type: replace-cross Abstract: Grammatical Error Correction (GEC) and feedback play a vital role in supporting second language (L2) learners, educators, and examiners. While
arXiv:2511.01061v2 Announce Type: replace Abstract: Backpropagation (BP) powers modern deep learning, but it must hold every activation in memory until a global backward sweep consumes it, and that sw
arXiv:2610.15111v1 Announce Type: cross Abstract: Data and the governing partial differential equations (PDEs) of continuous-time dynamical systems provide rich structure for statistical learning. A c
arXiv:2610.14940v1 Announce Type: new Abstract: Lifelong learning enables artificial systems to adapt to changing environments. To achieve this, an effective artificial learner should dynamically reor
arXiv:2610.13998v1 Announce Type: new Abstract: This paper proposes a hybrid reinforcement learning trading framework integrating intraday market data with transformer-based financial sentiment signal
arXiv:2610.15757v1 Announce Type: cross Abstract: Sentiment analysis is a key task in Natural Language Processing that determines the polarity of opinions in text. For low-resource languages like Mara
arXiv:2506.02841v5 Announce Type: replace-cross Abstract: Multi-agent reinforcement learning (MARL) methods have achieved state-of-the-art results on a range of multi-agent tasks. Yet, MARL algorithms
arXiv:2610.15871v1 Announce Type: cross Abstract: We study stationary discrete-time mean-field games with finite state and action spaces under the average-reward criterion, with an entropy-regularized
arXiv:2610.18790v1 Announce Type: new Abstract: Long-term robot autonomy depends on more than effective action generation: a policy must recognize when its behavior is no longer sufficiently supported
arXiv:2602.09506v4 Announce Type: replace Abstract: Contrastive learning (CL) is a predominant technique in image classification, but they showed limited performance with an imbalanced dataset. Recent
arXiv:2610.16149v1 Announce Type: cross Abstract: Learning equilibria from data is difficult when several decision makers interact indefinitely and the system state has no prescribed bounds. We examin
arXiv:2610.15933v1 Announce Type: new Abstract: Predictive coding networks (PCNs) promise properties not offered by backpropagation-trained networks: learning from purely local information, a single n
arXiv:2610.16268v1 Announce Type: new Abstract: Test-time-training (TTT) layers update fast-weight memory while processing an input sequence. A gradient-based update, however, does not by itself estab
arXiv:2610.16166v1 Announce Type: new Abstract: Interactive world models must capture how multiple participants jointly change a shared environment while observing different parts of it. Competitive g
arXiv:2610.16411v1 Announce Type: new Abstract: Deploying robots in human-shared environments requires deciding not only how to navigate, but also when dedicated social signals are worth emitting. Cla
arXiv:2610.18534v1 Announce Type: new Abstract: Flow Matching has recently become popular as a technique for generative modeling with applications in many domains. In the standard Flow Matching formul
arXiv:2610.14324v1 Announce Type: new Abstract: Foundation models like V-JEPA are increasingly deployed across a heterogeneous edge-cloud continuum spanning smart glasses, phones, robots, and servers.
arXiv:2610.17326v1 Announce Type: new Abstract: Household robots must successfully navigate im-perfect circumstances, both in their internal models and the external world. We introduce a benchmark of
arXiv:2610.17898v1 Announce Type: new Abstract: Sparse autoencoders decompose language model representations into interpretable features, but feature interpretation in this literature remains predomin
arXiv:2509.17287v3 Announce Type: replace-cross Abstract: Visual teach-and-repeat (VT&R) navigation enables robots to autonomously traverse previously demonstrated paths using visual feedback. We pres
arXiv:2610.16172v1 Announce Type: new Abstract: Recent multimodal large language models (MLLMs) achieve strong results on video question answering, yet often fail to recover the temporal structure tha
arXiv:2610.17724v1 Announce Type: cross Abstract: Long-horizon, semi-verifiable agentic tasks often rely on rubric-based evaluation, but the evidence needed to assess these tasks can be spread across
arXiv:2610.14609v1 Announce Type: new Abstract: Determining whether an image is AI-generated does not establish whether the situation it depicts is factually supported. We formulate Image Factuality A
arXiv:2610.16879v1 Announce Type: new Abstract: The rapid spread of face forgeries on the Web challenges the credibility of visual content. In practical Web environments, manipulated media originate f
arXiv:2610.15244v1 Announce Type: new Abstract: Self-evolving mechanisms let vision-language model (VLM) agents continually adapt through evolving memory, but they also allow malicious behavior to eme
arXiv:2610.16679v1 Announce Type: new Abstract: Tool-augmented vision-language agents compose perception and measurement to reason about spatial relationships, but effective execution also requires tr
arXiv:2610.14948v1 Announce Type: new Abstract: Temporal point processes are used both to measure market mechanisms, for example how fast prices absorb news and how much of the reaction is the market
arXiv:2610.17980v1 Announce Type: new Abstract: Plurality-voting ensembles aggregate the predictions of multiple base classifiers and output the most voted class, with ties typically broken at random.
arXiv:2610.18856v1 Announce Type: new Abstract: Persistent homology summarizes the topological evolution of a graph as persistence diagrams (PDs). Generating graphs whose topology matches a target des
arXiv:2610.15166v1 Announce Type: new Abstract: Coding agents are increasingly evolving beyond reproducing what a world looks like toward constructing executable worlds that capture how a world works.
arXiv:2511.20088v3 Announce Type: replace Abstract: In recent years, VAD (Visual Anomaly Detection) has attracted significant attention due to its high interpretability, as it provides visual explanat
arXiv:2610.16447v1 Announce Type: cross Abstract: The estimation of heterogeneous treatment effects is a central objective of causal inference. However, state-of-the-art algorithms to solve this task
arXiv:2610.15241v1 Announce Type: cross Abstract: Hoffman constants quantify the distance to the solution set of a polyhedral system in terms of its residual; they control error bounds, geometric cond
arXiv:2610.16329v1 Announce Type: new Abstract: Accurate breast cancer risk prediction from screening mammography is essential for improved risk stratification and personalized screening. It can benef
arXiv:2610.16187v1 Announce Type: cross Abstract: Existing cumulative regret guarantees for Bayesian optimization (BO) do not necessarily characterize the quality of the algorithm's final output. This
arXiv:2610.14817v1 Announce Type: cross Abstract: State-of-the-art beat tracking is based on neural networks that model beats and downbeats as individual events, often followed by a separate Dynamic B
arXiv:2610.17734v1 Announce Type: new Abstract: Exploration bounds learning efficiency in reinforcement learning with verifiable rewards (RLVR). Current methods explore mostly through independent samp
arXiv:2610.15207v1 Announce Type: new Abstract: Large Language Models (LLMs) have been shown to be computationally expensive and vulnerable to jailbreak attacks, in which adversarial prompts bypass sa