Knowledge catalogue
arXiv:2606.21613v1 Announce Type: new Abstract: Scaling wildlife monitoring for real-world conservation deployments requires automated analysis of smart sensors that operate under severe annotation sc
arXiv:2606.22347v1 Announce Type: new Abstract: Identity-Preserving Text-to-Video Generation (IPT2V) seeks to synthesize a temporally coherent video from a reference image and a textual description, w
arXiv:2606.20725v1 Announce Type: new Abstract: Accurate, up-to-date representations of road structures are critical for the safe operation of autonomous vehicles. Existing systems rely either on cost
arXiv:2606.21212v1 Announce Type: new Abstract: Causal discovery is critical for understanding complex data-generating mechanisms, yet traditional algorithms often struggle with highly non-linear and
arXiv:2606.22494v1 Announce Type: cross Abstract: Sign language is a primary mode of communication for the global deaf and hard-of-hearing community, yet automated tools that recognize sign gestures f
arXiv:2010.14694v4 Announce Type: replace-cross Abstract: This paper integrates deep neural networks (DNNs) into structural models to increase flexibility and capture rich heterogeneity while preservi
arXiv:2606.21036v1 Announce Type: cross Abstract: In many domains, practitioners seek models that produce accurate forecasts while faithfully capturing latent system dynamics. Existing approaches typi
arXiv:2606.22314v1 Announce Type: cross Abstract: Path-based attribution methods such as Integrated Gradients (IG) are widely adopted for their strong axiomatic properties and effectiveness in attribu
arXiv:2606.22982v1 Announce Type: new Abstract: Multi-arm manipulation demands precise spatiotemporal coordination, yet many centralized approaches scale poorly as team size increases. To address this
arXiv:2606.23626v1 Announce Type: new Abstract: Can representations learned for image generation also support the evaluation of generated images? We study text-to-image reward prediction as a downstre
arXiv:2606.22952v1 Announce Type: cross Abstract: This technical report presents submission systems for Task 7(domain-incremental audio classification) of the DCASE 2026 Challenge. The main obstacle i
arXiv:2606.20811v1 Announce Type: cross Abstract: We study the problem of system identification in heterogeneous settings, where different systems may follow distinct underlying dynamics. Existing clu
arXiv:2606.20924v1 Announce Type: new Abstract: In multi-object text-to-image (T2I) diffusion, ensuring semantic consistency between textual prompts and generated visual content is crucial for image s
arXiv:2606.22744v1 Announce Type: new Abstract: Predictive coding networks (PCNs) offer a biologically-plausible, local-learning alternative to back-propagation of errors (backprop). Nevertheless, the
arXiv:2606.19164v2 Announce Type: replace Abstract: Model merging aims to enable multi-task learning by integrating the capabilities of multiple models fine-tuned from the same pre-trained checkpoint
arXiv:2606.20611v1 Announce Type: cross Abstract: Recent research in educational data mining, especially knowledge tracing, has focused on predicting learners' future knowledge states to support adapt
arXiv:2509.23946v3 Announce Type: replace Abstract: Many LLMs plan before they act, yet planning and execution are often still entangled in one long generation trace, enforced only through prompts, or
arXiv:2606.22346v1 Announce Type: cross Abstract: Principled regression for stochastic processes is a long-standing challenge with deep connections to scientific inverse problems. We introduce Flow An
arXiv:2606.23293v1 Announce Type: new Abstract: 6D pose estimation is a key task in computer vision and embodied AI, widely used in robotic manipulation, augmented reality, etc. Existing methods direc
arXiv:2602.06226v2 Announce Type: replace Abstract: The ubiquity of monocular videos capturing daily hand-object interactions presents a valuable resource for embodied intelligence. While 3D hand reco
arXiv:2502.10178v2 Announce Type: replace Abstract: While transformer-based language models have driven the AI revolution thus far, their computational complexity has spurred growing interest in viabl
arXiv:2606.23312v1 Announce Type: new Abstract: Operating in complex real-world environments requires robots to understand their surroundings on a functional semantic level. This demands a detailed mu
arXiv:2512.13491v3 Announce Type: replace-cross Abstract: We inspect the deductive connection between the neural scaling law and Zipf's law -- two statements discussed in machine learning and quantita
arXiv:2606.22251v1 Announce Type: new Abstract: Tactile sensing enables robots to perceive rich contact information at the grasp, supporting tasks such as object recognition, in-hand pose estimation,
arXiv:2606.22741v1 Announce Type: new Abstract: Can one graph represent every kind of LLM agent's run? A trace records what each step did, never what it relied on, the state it read, and the results i
arXiv:2512.24946v2 Announce Type: replace Abstract: Existing film-restoration methods frequently fail under fast motion, producing limb disappearance and structural distortion due to inaccurate motion
arXiv:2606.19636v2 Announce Type: replace Abstract: Math and science reasoning benchmarks rely on pass@k, the fraction of sampled chains that reach gold, as the canonical per-example difficulty signal
arXiv:2606.21633v1 Announce Type: new Abstract: Diffusion LLMs (dLLMs) improve GPU utilization over autoregressive decoding by generating multiple tokens per forward pass, but their KV cache still gro
arXiv:2606.22834v1 Announce Type: new Abstract: We present homographic navigation, a geometry-centric framework for guiding camera acquisition toward precise capture of planar regions. Rather than tre
arXiv:2606.22935v1 Announce Type: new Abstract: Deep neural networks have witnessed remarkable advancements in recent years and have become integral to various applications. However, alongside these d
arXiv:2606.20624v1 Announce Type: cross Abstract: Significant progress has been made in aligning LLMs with target value functions. We argue that, even when an LLM has been well aligned in (post-)train
arXiv:2503.03579v2 Announce Type: replace-cross Abstract: Spoken instructions in robot-to-human handovers may specify either an object ('the cup') or an intended use ('pour water'); in both cases, suc
arXiv:2606.22725v1 Announce Type: new Abstract: Facial expression recognition (FER) is inherently ambiguous: human annotators frequently disagree, and models deployed in real environments face distrib
arXiv:2606.21975v1 Announce Type: cross Abstract: Despite its massive player base and complex hidden-information dynamics, Indian Rummy has received no reinforcement learning attention. Existing agent
arXiv:2606.20686v1 Announce Type: new Abstract: Shared-space transportation operation requires low-speed autonomous platforms to navigate safely and efficiently among pedestrians, service robots, micr
arXiv:2606.23589v1 Announce Type: new Abstract: Long-horizon robot manipulation remains challenging because similar observations may occur at different execution stages, while the appropriate action d
arXiv:2606.22369v1 Announce Type: cross Abstract: In this paper, we present Kiwano, an open-source toolkit designed to advance research and evaluation for speaker verification. Kiwano provides a light
Krea 2 is back and this time the weights are OPEN. This open source release ships with two models designed to work together — @krea_ai 2 RAW and Krea 2 Turbo. RAW is for training, Turbo is for inferen
arXiv:2606.20958v1 Announce Type: new Abstract: Modeling soft robot dynamics is challenging due to their continuum structure and typically nonlinear dynamics. Creating models based on first-order prin
arXiv:2606.22076v1 Announce Type: new Abstract: Single-reference unseen object 6D pose estimation reduces object onboarding by estimating poses of arbitrary novel objects from only one reference view.
arXiv:2606.23625v1 Announce Type: new Abstract: Most imitation learning methods assume full observability in table-top settings. In practice, objects are often occluded, requiring robots to both searc
arXiv:2606.23208v1 Announce Type: new Abstract: Deep Learning (DL) has advanced various fields by extracting complex patterns from large datasets. However, the computational demands of DL models pose
arXiv:2606.21292v1 Announce Type: new Abstract: We present Casper3D, a lightweight probabilistic framework for converting noisy multi-view 2D foundation-model embeddings into a latent 3D semantic repr
arXiv:2606.23653v1 Announce Type: new Abstract: Accurate volume and surface area estimation is critical for diverse applications, from marine ecology to medical diagnostics. However, existing methods
arXiv:2606.21968v1 Announce Type: new Abstract: Vision-Language Models (VLMs) struggle as query-relevant objects become smaller. To address this, recent training-free approaches dynamically retrieve a
arXiv:2506.16584v3 Announce Type: replace-cross Abstract: People judge interactions with large language models (LLMs) as successful when outputs match what they want, not what they type. Yet LLMs are
arXiv:2606.23489v1 Announce Type: cross Abstract: Meshes are among the most common 3D scene representations, but directly generating meshes is challenging because the representation contains important
arXiv:2606.22702v1 Announce Type: new Abstract: Traditional supervised methods for structured visual recognition tasks -- such as object detection, segmentation, and scene graph generation -- often pr
arXiv:2606.23061v1 Announce Type: new Abstract: Motion instruction generation in cross-video comparison aims to produce corrective feedback that describes the differences between a query and a referen
arXiv:2606.21088v1 Announce Type: new Abstract: Achieving robust and generalizable manipulation across diverse environments remains a fundamental challenge in embodied robotics. Recent world action mo
arXiv:2509.18671v2 Announce Type: replace Abstract: Determining where to execute the manipulation policy is a fundamental challenge in mobile manipulation. Most approaches have formulated this as a ge
arXiv:2606.20689v1 Announce Type: new Abstract: Neonatal jaundice (hyperbilirubinemia) is one of the most common conditions affecting newborns worldwide, with India alone recording roughly 15 million
arXiv:2606.21061v1 Announce Type: new Abstract: Stochastic segmentation seeks to represent multiple plausible masks for a single image, which is essential in safety- and quality-critical applications
arXiv:2606.22200v1 Announce Type: new Abstract: We study regression-based data fusion under uncertainty, where multiple noisy and biased measurement sources are available but ground-truth labels are a
arXiv:2606.22946v1 Announce Type: new Abstract: Neural operators learn mappings between function spaces, but are typically developed with dense input-output training fields and fully observed inputs a
arXiv:2606.22696v1 Announce Type: new Abstract: We propose NullFlow, a principled framework for one-step generative image reconstruction. Our key idea is to confine the generative flow to a measuremen
arXiv:2606.22617v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable performance on 2D visual tasks, yet enhancing their spatial intelligence for real-worl
arXiv:2606.23668v1 Announce Type: new Abstract: Large Language Models (LLMs) are frequently portrayed as general-purpose solvers capable of solving arbitrary tasks. We argue that this view overlooks a
arXiv:2606.22352v1 Announce Type: new Abstract: Dictionary learning has long been studied from both optimization and probabilistic perspectives. While formulations with element-wise sparsity regulariz
arXiv:2606.22357v1 Announce Type: cross Abstract: Language models are widely used in assistant settings, where controlling behavioral attributes is often essential. Activation steering modifies hidden