Knowledge catalogue
arXiv:2504.01527v2 Announce Type: replace Abstract: Avoiding the risk of undefined categorical labels using nearest neighbor interpolation overlooks the risk of exacerbating pixel level annotation err
arXiv:2605.10438v1 Announce Type: cross Abstract: Current 3D tokenizers largely treat representation as spatial compression: compact codes reconstruct surface geometry, but leave component ownership a
arXiv:2605.10780v1 Announce Type: cross Abstract: Representation autoencoders that reuse frozen pretrained vision encoders as visual tokenizers have achieved strong reconstruction and generation quali
arXiv:2605.09146v1 Announce Type: new Abstract: Humanoid Visual Search (HVS) requires agents to actively explore immersive 360^irc environments. While prior methods treat this as a monolithic task rel
arXiv:2510.07500v2 Announce Type: replace Abstract: We study black-box detection of machine-generated text under practical constraints: the scoring model (proxy LM) may mismatch the unknown source mod
arXiv:2605.09134v1 Announce Type: new Abstract: Reinforcement learning for program repair is hindered by sparse execution feedback and coarse sequence-level rewards that obscure which edits actually f
arXiv:2603.04783v2 Announce Type: replace Abstract: While LLMs demonstrate strong reasoning capabilities when provided with full information in a single turn, they exhibit substantial vulnerability in
arXiv:2605.10195v1 Announce Type: new Abstract: Tree-of-Thought (ToT) reasoning structures Large Language Model (LLM) inference as a tree-based search, demonstrating strong potential for solving compl
arXiv:2605.08862v1 Announce Type: cross Abstract: Reinforcement Learning (RL) has become a cornerstone for improving the performance of Large Language Models (LLMs). However, its rollout phase constit
arXiv:2605.10241v1 Announce Type: new Abstract: Natural language understanding (NLU) is integral to task-oriented dialog systems, but demands a considerable amount of annotated training data to increa
arXiv:2504.21228v3 Announce Type: replace-cross Abstract: Large Language Models (LLMs) are susceptible to indirect prompt injection attacks, where the model inadvertently responds to instructions inje
arXiv:2605.09279v1 Announce Type: cross Abstract: Volumetric video (VV) streaming enables real-time, immersive access to remote 3D environments, powering telepresence, ecological monitoring, and robot
arXiv:2605.09245v1 Announce Type: new Abstract: Multi-camera multi-object tracking (MCMOT) faces significant challenges in maintaining consistent object identities across varying camera perspectives,
arXiv:2605.09702v1 Announce Type: cross Abstract: Multi-judge evaluation is increasingly used to assess LLMs and reward models, and the prevailing heuristic is to curate: keep the most accurate judges
arXiv:2605.10419v1 Announce Type: cross Abstract: This paper investigates the effectiveness of large language models (LLMs) in answering questions over datasets. We examine their performance in two sc
arXiv:2605.08439v1 Announce Type: new Abstract: Accurately communicating the side effects of cancer treatments to cancer survivors is critical, particularly in settings such as informed consent, where
arXiv:2605.08965v1 Announce Type: new Abstract: Despite strong performance of Multimodal Large Language Models (MLLMs) on multimodal tasks, predicting whether and why an image is persuasive remains ch
arXiv:2605.10468v1 Announce Type: new Abstract: Muon has emerged as an efficient alternative to Adam for pretraining, yet remains underused for fine-tuning. A key obstacle is that most open models are
arXiv:2605.06638v2 Announce Type: replace Abstract: Reinforcement learning (RL) has been applied to improve large language model (LLM) reasoning, yet the systematic study of how training scales with t
arXiv:2605.10794v1 Announce Type: cross Abstract: Language models are deployed in settings that require compartmentalization: system prompts should not be disclosed, chain-of-thought reasoning is hidd
arXiv:2605.09795v1 Announce Type: new Abstract: This paper presents our systems and results for the Hope Speech Detection in Code-Mixed Tulu Language shared task at the Sixth Workshop on Speech, Visio
arXiv:2605.08663v1 Announce Type: new Abstract: We propose CAST, a dual-stream architecture that utilizes channel-aware spatial transfer learning for isolated sign language recognition addressing the
arXiv:2605.09016v1 Announce Type: new Abstract: Neural operators have emerged as powerful data-driven solvers for PDEs, offering substantial acceleration over classical numerical methods. However, exi
arXiv:2605.09223v1 Announce Type: new Abstract: Understanding long videos with multimodal large language models (MLLMs) requires selecting a small subset of informative frames under strict computation
arXiv:2605.09663v1 Announce Type: cross Abstract: Machine learning classifiers in dynamic environments face concept drift -- changes in the data-generating process that degrade performance. Convention
arXiv:2605.08333v1 Announce Type: cross Abstract: Retrieval-Augmented Generation (RAG) is sensitive to the vast hyperparameters of the retriever and generator, yet optimizing them using given queries
arXiv:2605.10290v1 Announce Type: cross Abstract: This paper aims at analyzing the regularization effect that data augmentation induces on supervised regression methods in the proportional regime, whe
arXiv:2603.05495v2 Announce Type: replace Abstract: To scale optimization and simulation, prior work has explored training machine-learning surrogates that map problem parameters to solutions inexpens
arXiv:2605.09975v1 Announce Type: new Abstract: Physics-informed neural networks (PINNs) are a promising approach for solving partial differential equations (PDEs). Their training, however, is often d
arXiv:2605.09846v1 Announce Type: cross Abstract: In new media art creation, the mapping between vision and hearing is often subjective. As a classic carrier of sound visualization, Chladni patterns h
arXiv:2603.21901v2 Announce Type: replace Abstract: Video subtitle removal aims to distinguish text overlays from background content while preserving temporal coherence. Existing diffusion-based metho
arXiv:2605.09858v1 Announce Type: new Abstract: Multi-Object Tracking (MOT) in dynamic environments relies on robust temporal reasoning to maintain consistent object identities over time. Transformer-
arXiv:2605.10163v1 Announce Type: cross Abstract: Recent work on causal abstraction, in particular graphical approaches focusing on causal structure between clusters of variables, aims to summarize a
arXiv:2511.06894v3 Announce Type: replace-cross Abstract: Reconstruction-based methods are a dominant paradigm in time series anomaly detection (TSAD), however, their near-universal reliance on Mean S
arXiv:2605.08735v1 Announce Type: new Abstract: Recent 'Thinking with Video' approaches use Video Generation Models (VGMs) for visual reasoning by producing temporally coherent Chain-of-Frames as reas
arXiv:2605.08750v1 Announce Type: cross Abstract: Natural language is widely used to describe, prompt, and control audio systems, but rarely serves as the representation carrying audio itself. We intr
arXiv:2605.08885v1 Announce Type: new Abstract: SO(3) equivariant graph neural networks have become the dominant paradigm for atomistic foundation models, achieving high accuracy and data efficiency b
arXiv:2512.00175v3 Announce Type: replace-cross Abstract: Identifying causal effects in the presence of unmeasured variables is a fundamental challenge in causal inference, for which proxy variable me
arXiv:2605.10642v1 Announce Type: new Abstract: Pretrained diffusion models provide powerful learned priors, but in scientific sampling the target distribution often depends on physical context that i
arXiv:2601.21164v3 Announce Type: replace Abstract: Plane Geometry Problem Solving (PGPS) is a multimodal reasoning task that aims to solve a plane geometric problem based on a geometric diagram and p
arXiv:2605.10533v1 Announce Type: new Abstract: In causal inference, confounders are variables that influence both treatment decisions and outcomes. However, unlike as in randomized clinical trials, t
arXiv:2512.03706v2 Announce Type: replace-cross Abstract: Coarse graining (CG) is an important task for efficient modeling and simulation of complex multi-scale systems, such as the conformational dyn
arXiv:2605.09968v1 Announce Type: new Abstract: Every adaptive learning system must alternate between two operations: consolidating what it already knows and expanding into new evidence. We propose Co
arXiv:2605.09085v1 Announce Type: new Abstract: Density estimation is a central primitive in probabilistic modeling, yet continuous, discrete, and mixed-variable domains are often treated by separate
arXiv:2602.08606v2 Announce Type: replace-cross Abstract: Motivated by applications in conditional sampling, given a probability measure mu and a diffeomorphism phi, we consider the problem of simulta
arXiv:2605.09112v1 Announce Type: cross Abstract: Selecting a coherent sequence or subset of elements is a fundamental problem in structured prediction, arising in tasks such as detection, trajectory
arXiv:2605.08781v1 Announce Type: new Abstract: AI-assisted bridge defect inspection often produces bounding boxes with crude geometry or raster masks that are costly to store, transmit, and reuse. Th
arXiv:2605.08561v1 Announce Type: cross Abstract: Density estimation and reliable prediction regions for outputs are crucial in supervised and unsupervised learning. While conformal prediction effecti
arXiv:2605.08727v1 Announce Type: cross Abstract: Learned image compression (LIC) integrates deep neural networks (DNNs) to map high-dimensional images into compact latent representations, reducing re
arXiv:2605.08856v1 Announce Type: new Abstract: Autoregressive neural simulators now match classical solvers on short-horizon prediction of physical systems, yet their accuracy degrades rapidly when r
arXiv:2602.05902v2 Announce Type: replace-cross Abstract: Post-training quantization (PTQ) enables efficient deployment of large language models by mapping pretrained weights to low-bit formats withou
arXiv:2602.05243v2 Announce Type: replace-cross Abstract: Transformers achieve strong accuracy but incur high compute and memory cost. Structured pruning reduces inference cost, but most methods rely
arXiv:2605.09528v1 Announce Type: new Abstract: We present Version 2 of system Cplus2ASP, which implements the definite fragment of action language C+. Its input language is fully compatible with the
arXiv:2605.09414v1 Announce Type: new Abstract: Emojis are widely used in online financial communication, but it is unclear whether they provide transferable sentiment signals across languages, platfo
arXiv:2605.09833v1 Announce Type: cross Abstract: This paper studies cross-domain lossy compression through the lens of minimum entropy coupling (MEC) with rate and classification constraints. In this
arXiv:2605.09242v1 Announce Type: cross Abstract: Automated grading of diabetic retinopathy (DR) faces several critical challenges: subtle inter-grade visual distinctions in fine-grained lesion patter
arXiv:2605.09802v1 Announce Type: cross Abstract: Vision-language models (VLMs) enable text-guided object detection but degrade severely under cross-view scenarios where ground and aerial viewpoints d
arXiv:2601.21698v2 Announce Type: replace-cross Abstract: Curriculum learning changes the order of pretraining data, but it remains unclear how ordering changes the learning dynamics. We pretrain mode
arXiv:2503.03481v2 Announce Type: replace Abstract: This work demonstrates that the non-stop flights of three or more carriers are compatible with holding a constant pose of a cable-suspended load. It
arXiv:2605.09400v1 Announce Type: new Abstract: Batch selection is crucial for improving both training efficiency and predictive performance in deep multi-label classification (MLC). Existing batch se