Knowledge catalogue
arXiv:2609.30379v1 Announce Type: cross Abstract: Variable-size inputs are common in deep learning, but dense batching allocates a shared envelope and spends computation on padding. The cost multiplie
arXiv:2609.30947v1 Announce Type: new Abstract: Visual odometry is essential for autonomous navigation in GPS-denied environments, yet RGB-based methods remain vulnerable to motion blur, challenging i
arXiv:2609.31401v1 Announce Type: new Abstract: Prior work established that a probe can decode an in-context binding on model errors and that probe-guided steering can repair some of them. We follow p
arXiv:2609.30809v1 Announce Type: cross Abstract: We investigate the use of neural network solvers for infinity and p-Laplace problems, which are fundamental in nonlinear analysis and have practical a
arXiv:2609.31568v1 Announce Type: new Abstract: AI tutoring could markedly improve learning outcomes for students in developing regions such as Vietnam, yet the two obvious paths both fall short. Clou
arXiv:2512.08996v2 Announce Type: replace-cross Abstract: Radiotherapy planning is a highly complex process that often varies significantly across institutions and individual planners. Most existing d
arXiv:2609.31103v1 Announce Type: cross Abstract: Spatial reasoning with metric constraints requires linking objects to geometric measurements and preserving their numerical content during language re
arXiv:2609.30759v1 Announce Type: new Abstract: The utility of flexible continuum mechanisms for dexterous navigation is often impaired by their low stiffness, making them ineffective at manipulation
arXiv:2605.05725v2 Announce Type: replace Abstract: Time-series anomaly detection often returns scores or intervals, while analysts need to understand the abnormal behavior and the evidence supporting
arXiv:2609.31250v1 Announce Type: new Abstract: We report fine-grained, deterministic instability in Dynamic Tensor Rematerialization (DTR), an online eviction policy for memory-constrained DNN traini
arXiv:2609.30863v1 Announce Type: cross Abstract: The emergence of AI agents is expected to reshape software engineering by moving beyond AI as assistants towards systems capable of planning, executin
arXiv:2609.30461v1 Announce Type: new Abstract: Off-road traversability is direction-dependent and vehicle specific, yet most global maps assign a single isotropic cost to each location. Existing lear
arXiv:2609.31456v1 Announce Type: new Abstract: Vision-language models (VLMs) often struggle with compositional reasoning tasks, but the reasons for this underperformance remain unclear. A common hypo
arXiv:2609.31215v1 Announce Type: new Abstract: Large language models (LLMs) as a judge enable scalable evaluation, but their judgments can be sensitive to response order and, even after removing such
arXiv:2609.31454v1 Announce Type: cross Abstract: Federated learning (FL) data corruption can affect either inputs or labels, but it remains unclear whether input-conditional uncertainty and predictio
arXiv:2609.30752v1 Announce Type: new Abstract: Many deep learning approaches to RNA secondary structure prediction have recently been proposed. They typically output a weight matrix W where W_{ij} is
arXiv:2609.31399v1 Announce Type: new Abstract: Multimodal emotion recognition (MER) increasingly pairs EEG with speech, treating internal neural signals and external vocal expression as informative v
arXiv:2305.15394v3 Announce Type: replace Abstract: Decision trees are interpretable models that are well-suited to non-linear learning problems. Much work has been done on extending decision tree lea
arXiv:2609.30658v1 Announce Type: cross Abstract: Implicit neural representations (INRs) have gained momentum in scientific visualization due to their compactness and scalability to large datasets, ma
arXiv:2609.31061v1 Announce Type: new Abstract: Application developers of distributed learning services face challenges that a typical federated learning loop does not address. Specifically, the model
arXiv:2603.04736v2 Announce Type: replace Abstract: Learning a transport model that maps a source distribution to a target distribution is a canonical problem in machine learning, but scientific appli
arXiv:2609.30274v1 Announce Type: cross Abstract: Machine Learning and more specifically Deep Learning involves solving large scale nonconvex optimization problems. Several algorithms have been propos
arXiv:2609.30484v1 Announce Type: new Abstract: While large language models (LLMs) have achieved remarkable linguistic capabilities, a profound question lingers at their core: do these models truly co
arXiv:2607.11347v2 Announce Type: replace Abstract: Neural networks increasingly inform consequential decisions, making their reliability increasingly important. Yet their internal mechanisms provide
arXiv:2609.31130v1 Announce Type: new Abstract: We empirically investigate Question Under Discussion based modelling in naturalistic dialogue by studying whether the salience of generated potential qu
arXiv:2609.30768v1 Announce Type: new Abstract: Thinking in reasoning language models (RLMs) has been subject to debate on whether it resolves or amplifies bias. Prior works have shown competing concl
arXiv:2511.20561v3 Announce Type: replace-cross Abstract: Recent years have witnessed significant progress in Unified Multimodal Models, yet a fundamental question remains: Does understanding truly in
arXiv:2609.30977v1 Announce Type: cross Abstract: Uniform discrete diffusion models (UDMs) commonly use explicit time conditioning, but we find that it can often be unnecessary in practice. In this pa
arXiv:2609.30540v1 Announce Type: cross Abstract: Text-to-music systems are assessed on audio quality and on how faithfully the music follows its prompt, and the CLAP score, the cosine similarity betw
arXiv:2609.31108v1 Announce Type: new Abstract: High dynamic range (HDR) video reconstruction from al-ter-na-ting-exposure sequences remains challenging, especially in regions with extreme luminance v
arXiv:2609.31412v1 Announce Type: new Abstract: We present the dynamic rotation-stacked visibility graph (dRVG), an online motion planner that guides polygonal robots to specified goals in initially u
arXiv:2609.31112v1 Announce Type: new Abstract: Vision-language models (VLMs) enable open-vocabulary reasoning for robot manipulation, but their high inference latency limits responsiveness in dynamic
arXiv:2609.31349v1 Announce Type: cross Abstract: Large video diffusion models offer expressive priors for embodied prediction and learning, yet their many-step sampling remains costly for interactive
arXiv:2609.30556v1 Announce Type: new Abstract: We study dynamic regret in online convex optimization with an indicator switching cost: a fixed penalty incurred whenever two consecutive decisions diff
arXiv:2601.22419v2 Announce Type: replace-cross Abstract: Pooled testing uses one test to certify several agents as healthy when the pooled result is negative. We study a budget-constrained welfare pr
arXiv:2609.31047v1 Announce Type: cross Abstract: Agentic LLM workflows decide their execution paths at runtime. Downstream computation may be predictable, or may have run before, yet it cannot begin
arXiv:2609.31551v1 Announce Type: cross Abstract: Disaggregating the two stages, Prefill and Decode, onto separate GPU pools is now a standard optimization for (text-only) LLM serving. However, multim
arXiv:2609.30882v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly used to assess long-form medical videos, but their effectiveness may depend on whether transcripts are pro
arXiv:2401.04282v2 Announce Type: replace Abstract: We introduce a model-agnostic framework for constrained post-hoc error correction in binary classifiers. Given a frozen base classifier, the method
arXiv:2606.20626v2 Announce Type: replace-cross Abstract: Safety benchmarks for language models are typically evaluated using static paradigms that treat all items as equally informative for all model
arXiv:2609.30417v1 Announce Type: new Abstract: As electric vehicle (EV) adoption increases, ensuring efficient and well-distributed charging infrastructure has become a critical challenge. While many
arXiv:2606.15848v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has shown strong potential for high-fidelity talking head synthesis. However, enabling fine-grained, interpretable, and
arXiv:2609.31207v1 Announce Type: cross Abstract: Achieving robust cross-embodiment generalization in imitation learning demands overcoming a critical representation flaw that inextricably entangles t
arXiv:2609.30272v1 Announce Type: cross Abstract: We present extbf{ENAS}, a hardware-aware Neural Architecture Search (NAS) framework that combines a static feasibility check, a cell-based search spac
arXiv:2609.30581v1 Announce Type: cross Abstract: Encrypted training relies on keeping server-side updates low-degree. This constraint traditionally excludes models whose weights inhabit a compact Lie
arXiv:2608.00008v2 Announce Type: replace Abstract: The local deployment of large language models (LLMs) is gaining traction due to privacy concerns and the desire for on-premise inference. However, t
arXiv:2609.30580v1 Announce Type: new Abstract: Virtual sensing repeatedly reconstructs physical fields from changing observations, often on a fixed geometry. We investigate how shared spatial computa
arXiv:2609.30849v1 Announce Type: new Abstract: Prior work has examined the self-consistency of LLM-generated explanations using surface-level perturbation methods. However, the strength of these pert
arXiv:2609.31199v1 Announce Type: cross Abstract: Large-scale Digital Surface Models (DSMs) can be produced cost-effectively from satellite images via stereo-photogrammetry. However, the resulting 3D
arXiv:2609.30572v1 Announce Type: new Abstract: Large language models are often post-trained on expert demonstrations using cross-entropy (CE), even when the downstream objective is not to imitate the
arXiv:2609.30929v1 Announce Type: new Abstract: Completed multi-horizon forecasts provide residual feedback for a fixed forecaster, but retaining full residual blocks increases auxiliary state. We pro
arXiv:2609.30611v1 Announce Type: cross Abstract: On Jan. 30, 2026, the U.S. Department of Justice released a mixed-media collection concerning Jeffrey Epstein, including about three million pages of
arXiv:2609.31368v1 Announce Type: cross Abstract: Tree-Adjoining Grammars (TAGs) have recently been introduced to Nonlinear System Identification (NLSI) as a means of encoding an entire model class as
arXiv:2609.30935v1 Announce Type: cross Abstract: Continual fine-tuning is essential for large language models (LLMs) to dynamically adapt to real-world environments, yet it inevitably suffers from ca
arXiv:2609.31506v1 Announce Type: cross Abstract: Large language models (LLMs) exhibit substantial performance disparities between high- and low-resource languages. Beyond lower task performance, they
arXiv:2609.30798v1 Announce Type: new Abstract: Real-time voice agents have moved from research prototypes to production deployments, yet the literature describing them is fragmented across three comm
arXiv:2609.30986v1 Announce Type: new Abstract: As large language models increasingly mediate information access, factually accurate and independent answers are critical. However, these models can exh
arXiv:2609.31415v1 Announce Type: new Abstract: Position-independent KV cache reuse aims to reduce latency in retrieval-augmented generation by reusing chunk-level KV caches across prompts. We show th
arXiv:2609.31138v1 Announce Type: new Abstract: As populations in developed countries age and labor shortages intensify, Cybernetic Avatars (CAs) are proposed to extend human capabilities through robo
arXiv:2609.30818v1 Announce Type: cross Abstract: Multi-modal planning is promising for autonomous driving by representing multiple plausible behaviors in ambiguous and long-tail scenarios. Existing m