Knowledge catalogue
arXiv:2608.16220v1 Announce Type: cross Abstract: Generating personalized dance videos from a reference image, text prompt, and audio track requires music-conditioned body motion. Singing-and-dancing
arXiv:2608.14943v1 Announce Type: new Abstract: Agent skills are often injected in full on every request, increasing token cost. We compare four content-preserving loading methods: Full, Skill Block,
arXiv:2608.14579v1 Announce Type: new Abstract: Logic synthesis optimization poses significant challenges due to exponentially growing search spaces, sparse reward signals, and diverse logic structure
arXiv:2608.16071v1 Announce Type: new Abstract: Pseudo-query generation can alleviate the supervision bottleneck for agent skill retrieval, but existing document-level approaches typically leave the r
arXiv:2608.15165v1 Announce Type: new Abstract: Large language model (LLM) agents can continually improve without parameter updates by converting historical experience into reusable procedural knowled
arXiv:2608.14944v1 Announce Type: cross Abstract: Natural-language interfaces can lower the barrier to programming robots, but existing systems struggle when users request complex tasks. While large l
arXiv:2606.19888v2 Announce Type: replace-cross Abstract: Modeling long-sequence medical time series data, such as electrocardiograms (ECG), poses significant challenges due to high sampling rates, mu
arXiv:2510.15911v3 Announce Type: replace-cross Abstract: The Sleeping Beauty problem is a problem of imperfect recall that has received considerable attention. One approach to solving the Sleeping Be
arXiv:2602.04525v3 Announce Type: replace-cross Abstract: Very-high-resolution remote-sensing imagery provides a scalable basis for delineating informal settlements, but sparse annotations, severe imb
arXiv:2508.09105v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) and its Multimodal Retrieval-Augmented Generation (MRAG) significantly improve the knowledge coverage and conte
arXiv:2608.14936v1 Announce Type: new Abstract: Small proxy models are commonly used to identify data mixtures for larger-scale training. We ask whether their training trajectories reveal another tran
arXiv:2608.14647v1 Announce Type: cross Abstract: Dirty-history rollouts make multi-turn on-policy self-distillation (OPSD) brittle: once a student emits an erroneous intermediate reply, later turns a
arXiv:2608.16409v1 Announce Type: new Abstract: Today, a neural system is almost always used in two phases -- trained, then deployed -- and in that regime it freezes twice: training ends, and the topo
arXiv:2608.16237v1 Announce Type: cross Abstract: Building operations are energy-inefficient. Artificial Intelligence (AI)-driven control systems promise benefits through optimization and predictive c
arXiv:2608.15958v1 Announce Type: new Abstract: Deciding whether a Sokoban puzzle is solvable is PSPACE-complete (Culberson, 1997): solutions can be exponentially long and there is no short certificat
arXiv:2608.15741v1 Announce Type: new Abstract: The one-stage planner YOPO maps a single depth image and the robot state directly to a set of candidate trajectories, trained by backpropagating through
arXiv:2608.15295v1 Announce Type: new Abstract: Foundation segmentation models excel at generating high-quality, class-agnostic masks, but they struggle to associate these proposals with specific targ
arXiv:2608.16172v1 Announce Type: new Abstract: At every re-observation point in a hierarchical Vision-Language-Action (VLA) system, two interface decisions must be made: when to terminate the current
arXiv:2608.15632v1 Announce Type: cross Abstract: Neural representations have become a central tool for studying the internal mechanisms of modern AI models, yet their complex high-dimensional structu
arXiv:2608.14725v1 Announce Type: new Abstract: We present a novel causal approach to interpretability for computer vision models that dynamically masks the input image prior to classification. The in
arXiv:2608.16008v1 Announce Type: new Abstract: Text-driven human motion editing aims to modify existing motion sequences according to natural language instructions while maintaining the structural co
arXiv:2608.15452v1 Announce Type: new Abstract: Current flow matching models learn to transport the source i.i.d. Gaussian noise into the target distribution of natural images, yet this source distrib
arXiv:2608.16878v1 Announce Type: cross Abstract: For any convex body KsubsetR^{n} containing a unit ball, the spectral gap of Hit-and-Run is Omega(1/(n^2 C_{mathsf{PI}})), where C_{mathsf{PI}} is the
arXiv:2608.15351v1 Announce Type: new Abstract: Nominal LoRA rank is a design parameter; calibrated spectral evidence is a separate inferential quantity. This article develops a finite-sample framewor
arXiv:2608.15548v1 Announce Type: cross Abstract: Machine unlearning (MU) aims to remove the influence of specific training data while preserving model utility. As the name suggests, MU can be viewed
arXiv:2606.12485v2 Announce Type: replace-cross Abstract: Training interactive web agents through imitation learning from expert trajectories has emerged as a highly effective approach. However, deter
arXiv:2608.14922v1 Announce Type: cross Abstract: Mechanistic interpretability has recently expanded to Vision Transformers (ViTs), with Sparse Autoencoders (SAEs) increasingly used as post-hoc tools
arXiv:2608.15001v1 Announce Type: cross Abstract: We construct spinning conformal fields from neural networks and the embedding formalism, computing their two-, three- and four-point functions in exam
arXiv:2608.16863v1 Announce Type: new Abstract: Generating photorealistic novel views from unposed images requires both 3D geometric understanding and the ability to synthesize unseen content. A natur
arXiv:2608.14713v1 Announce Type: cross Abstract: Robots operating in dark or poorly lit environments rely on onboard lights, which often produce uneven illumination that degrades downstream perceptio
arXiv:2608.16585v1 Announce Type: new Abstract: Video Diffusion Transformers (DiTs) spend most of their compute inside the Self-Attention operation, whose cost grows quadratically, O(n^2), with the nu
arXiv:2411.19289v4 Announce Type: replace Abstract: Dynamic visual-inertial odometry (VIO) requires reliable suppression of motion-corrupted measurements, yet prior semantic-assisted approaches depend
arXiv:2608.16553v1 Announce Type: new Abstract: Multi-preference alignment is often framed as scalarization: combine reward dimensions, then optimize. This leaves a temporal decision underspecified: w
arXiv:2608.16224v1 Announce Type: cross Abstract: By leveraging large-scale pretraining, LLMs can interpret diverse temporal expressions and question formulations without task-specific training. Howev
arXiv:2608.14861v1 Announce Type: cross Abstract: Data poisoning attacks pose serious security threats to Federated Learning (FL) systems in Computer Vision. Despite growing research attention, two ke
arXiv:2608.15089v1 Announce Type: new Abstract: Long-horizon agents can fail even when their underlying models can solve the constituent steps. They may lose track of mutable state, fail to reactivate
arXiv:2608.16309v1 Announce Type: cross Abstract: Static pruning is widely used to accelerate sparse neural retrieval, yet existing studies each validate their conclusions within a single custom pipel
arXiv:2608.16791v1 Announce Type: cross Abstract: Model Inversion Attacks (MIAs) aim to reconstruct representative training samples of target identities from face recognition models, exposing critical
arXiv:2608.16333v1 Announce Type: cross Abstract: On-policy distillation (OPD) aligns a student model with a teacher's logit distribution on student-generated trajectories. This approach has achieved
arXiv:2608.16469v1 Announce Type: new Abstract: Scene graph generation from surgical video enables a holistic and structured understanding of surgical scenes by modeling objects and their semantic rel
arXiv:2601.06404v2 Announce Type: replace Abstract: Federated Clustering (FC) faces a critical bottleneck in real-world scenarios, i.e., global clusters are rarely intact, often fragmenting into incom
arXiv:2608.14648v1 Announce Type: cross Abstract: In this study, we revisit three widely used techniques in vector search and utilize them to optimize vector embedding indexing through clustering: dim
arXiv:2608.16320v1 Announce Type: new Abstract: Streaming video understanding demands direct responses from the causally observed prefix of an unfolding video. Existing systems add inference-time memo
arXiv:2608.15139v1 Announce Type: new Abstract: Flow-based Vision-Language-Action (VLA) models are now widely used for continuous robotic manipulation, and online reinforcement learning (RL) is emergi
arXiv:2608.16050v1 Announce Type: cross Abstract: Spreadsheets are a primary medium for publishing tabular data, yet automatically extracting structured content from them remains difficult due to hete
arXiv:2608.15224v1 Announce Type: new Abstract: Reliable post-hoc evaluation asks whether already generated text satisfies a target criterion after generation. In this paper we study a focused frozen-
arXiv:2608.15665v1 Announce Type: new Abstract: Zeroth-order (ZO) optimization enables backpropagation-free fine-tuning of large language models, but existing ZO methods suffer from high-variance grad
arXiv:2608.15121v1 Announce Type: cross Abstract: Sufficient dimension reduction (SDR) seeks the minimal subspace of the predictors that captures the full conditional distribution of the response, whi
arXiv:2608.16110v1 Announce Type: new Abstract: Cold Start Active Learning (CSAL) is important in improving the performance of a medical image segmentation model with low annotation budget by querying
arXiv:2606.17215v2 Announce Type: replace Abstract: A certificate that removes outliers sees the data only through its low-degree moments, and an adversary exploits exactly this, hiding corruption whe
arXiv:2608.16546v1 Announce Type: new Abstract: Most super-resolution models learn from paired data by supervising only the final high-resolution output. This provides little control over how the pred
arXiv:2608.16058v1 Announce Type: new Abstract: Learning-based surgical robot autonomy requires large-scale demonstrations with synchronized videos and robot actions, but such data are exceedingly rar
arXiv:2608.14697v1 Announce Type: new Abstract: Steganography in large language models offers a way to embed hidden messages within natural-sounding text. Existing token and logit-level methods typica
arXiv:2608.14758v1 Announce Type: cross Abstract: For patients with Moyamoya disease, impaired cerebrovascular reserve (CVR) is an important hemodynamic criterion for recommending extracranial-to-intr
arXiv:2608.16380v1 Announce Type: cross Abstract: Monitoring war-induced damage to agricultural land in Ukraine is important for understanding threats to food security, environmental stability, and po
arXiv:2602.12381v2 Announce Type: replace Abstract: Recent generative models produce near-photorealistic images, challenging the trustworthiness of photographs. Synthetic image detection (SID) methods
arXiv:2608.15012v1 Announce Type: cross Abstract: The rapid advancement of large language models (LLMs) has created a growing asymmetry in cybersecurity, where attack accelerates toward autonomous exe
arXiv:2608.14953v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have opened opportunities to apply high-level code transformations to the field of code optimization, an
arXiv:2608.15968v1 Announce Type: new Abstract: Low-cost four-degree-of-freedom (DoF) arms are among the most accessible robotic platforms. But they are, in theory, underactuated for picking up in sit
arXiv:2608.15766v1 Announce Type: new Abstract: Humanoid robots are expected to traverse complex terrains, where the plantar support may vary dramatically due to foot placement errors, ground properti