Neural Bayesian Sequential Routing
arXiv:2605.26147v1 Announce Type: new Abstract: Human decision-making is sequential and uncertainty-aware, yet standard neural networks often rely on static, dense forward computation with limited vis
Knowledge catalogue
arXiv:2605.26147v1 Announce Type: new Abstract: Human decision-making is sequential and uncertainty-aware, yet standard neural networks often rely on static, dense forward computation with limited vis
arXiv:2410.00357v2 Announce Type: replace Abstract: Neural scaling laws play a pivotal role in the performance of deep neural networks and have been observed in a wide range of tasks. However, a compl
arXiv:2605.26942v1 Announce Type: new Abstract: LLMs deployed in high-stakes domains face fundamental reliability challenges: hallucinations, inconsistencies, and privacy vulnerabilities introduce una
arXiv:2605.26330v1 Announce Type: new Abstract: Small aerial robots are particularly well-suited for search and rescue in confined and hazardous environments due to their agility, low cost, and abilit
arXiv:2512.19602v2 Announce Type: replace Abstract: Large-scale medical biobanks provide imaging data complemented by extensive tabular information, such as clinical measurements or demographics. Howe
arXiv:2605.27219v1 Announce Type: new Abstract: Collaborative analysis of decentralized confidential datasets is important, but direct sharing of original datasets is often restricted by privacy and i
arXiv:2605.27306v1 Announce Type: new Abstract: We consider training classifiers for 3D medical images using only one binary label for the entire volume rather than a label for each 2D slice. In such
arXiv:2511.22882v3 Announce Type: replace Abstract: We introduce boundary quotients and present a framework for learning densities on manifolds that arise as boundary quotients of simpler domains. We
arXiv:2605.26844v1 Announce Type: new Abstract: On-policy distillation (OPD) trains a student on its own rollouts with token-level teacher supervision. Recent selective OPD methods exploit the non-uni
arXiv:2605.26232v1 Announce Type: new Abstract: Pre-trained video large language models excel at visual reasoning. However, they struggle when videos arrive with auxiliary streams, such as audio, dept
arXiv:2605.27194v1 Announce Type: new Abstract: Distilling demonstration effects into hidden-space interventions offers a lightweight alternative to full finetuning. However, existing multimodal varia
arXiv:2503.08600v3 Announce Type: replace Abstract: We introduce NSF-SciFy, a comprehensive dataset of scientific claims and investigation proposals extracted from National Science Foundation award ab
arXiv:2605.26584v1 Announce Type: new Abstract: Omnimodal large language models enable unified audio video understanding, but long joint token sequences make inference costly, and existing benchmarks
arXiv:2605.26944v1 Announce Type: cross Abstract: The problem of object pose and shape estimation has seen key advancements lately. Encoder-decoder (e.g., SAM3D, LRM, CRISP) and diffusion-based models
arXiv:2505.17163v2 Announce Type: replace-cross Abstract: Recent advancements in multimodal slow-thinking systems have demonstrated remarkable performance across various visual reasoning tasks. Howeve
arXiv:2508.01253v2 Announce Type: replace Abstract: Existing studies typically investigate domain shift and category shift as independent problems, however, in real-world scenarios, the two types of s
arXiv:2602.10104v2 Announce Type: replace-cross Abstract: Scaling action-controllable world models is limited by the scarcity of action labels. While latent action learning promises to extract control
arXiv:2603.16654v2 Announce Type: replace-cross Abstract: Evaluating the reasoning abilities of large language models (LLMs) solely from final answers can obscure failures in intermediate steps, espec
arXiv:2603.25152v3 Announce Type: replace Abstract: Retrieval-Augmented Generation (RAG) systems face significant challenges in complex reasoning, multi-hop queries, and domain-specific QA. While exis
arXiv:2605.26399v1 Announce Type: new Abstract: Understanding human gaze behavior is essential for complex scene comprehension and human-computer interaction. Traditional gaze following models are typ
arXiv:2605.26485v1 Announce Type: cross Abstract: We introduce OmniInteract, a streaming benchmark for real-time omnimodal large language models evaluated through native online inference over audio-vi
arXiv:2605.26641v1 Announce Type: new Abstract: Unified multimodal embedding spaces have become the standard interface for cross-modal retrieval and multimodal RAG, and recent audio-video-text (AVT) e
arXiv:2605.26322v1 Announce Type: new Abstract: Theory of Mind (ToM), the ability to infer others' knowledge, intentions, and emotions, is commonly evaluated in large language models (LLMs) using end-
arXiv:2605.26908v1 Announce Type: new Abstract: Exploiting the indistinguishability of objects in a probabilistic graphical model such as a factor graph is key to lifted probabilistic inference algori
arXiv:2605.26582v1 Announce Type: cross Abstract: Discrete diffusion models achieve strong performance in text and image generation, but their inference remains slow and must inherently balance sampli
arXiv:2605.26649v1 Announce Type: new Abstract: RGB-based imitation learning requires many demonstrations to generalize to unseen objects or scenes, motivating research into intermediate representatio
arXiv:2605.27083v1 Announce Type: new Abstract: Counterfactual tuning (CFT) has emerged as a promising paradigm for Large Language Model (LLM) unlearning by training models to generate alternative fic
arXiv:2605.26162v1 Announce Type: cross Abstract: Asynchronous decentralized federated learning (ADFL) eliminates central coordination and global synchronization, making it attractive for large-scale
arXiv:2605.26992v1 Announce Type: new Abstract: Vision-language models (VLMs) may memorize undesirable information from training data, motivating growing interest in machine unlearning. In this work,
arXiv:2605.26194v1 Announce Type: new Abstract: Clinical time-series learning is routinely constrained by small, heterogeneous cohorts and protocol drift, while its downstream use spans both classific
arXiv:2510.05864v2 Announce Type: replace Abstract: Large language models (LLMs) increasingly operate on long inputs, yet their behavior when harmful sentences are sparsely embedded within such inputs
arXiv:2605.26761v1 Announce Type: new Abstract: Multimodal instruction tuning is the de facto recipe for adapting vision language models (VLMs), yet instruction data are highly redundant, making data
arXiv:2605.26373v1 Announce Type: new Abstract: We study adversarial online learning with hidden-convex losses, i.e., nonconvex losses that become convex after a nonlinear reparameterization. Ghai, Lu
arXiv:2605.26526v1 Announce Type: new Abstract: Recent defenses for safeguarding open-weight large language models (LLMs) are intended to prevent adversarial usage. Underlying these defenses is an ass
arXiv:2602.04397v2 Announce Type: replace-cross Abstract: We study a setting in which two players play a (possibly approximate) Nash equilibrium of a bimatrix game, while a learner observes only their
arXiv:2605.26840v1 Announce Type: new Abstract: Reinforcement learning with evaluation metrics as rewards is widely used to enhance specific capabilities of language models. However, for tasks such as
arXiv:2605.27022v1 Announce Type: new Abstract: Causal analysis is a crucial task in many domains, including manufacturing, social science, and medicine. However, despite recent progress, the conceptu
arXiv:2601.21008v3 Announce Type: replace-cross Abstract: Operations Research practitioners debug infeasible models through an iterative process: inspecting Irreducible Infeasible Subsystems ( IIS), i
arXiv:2605.26831v1 Announce Type: new Abstract: Semantic mapping methods are increasingly used as intermediate scene representations for downstream robotic reasoning and manipulation, yet their evalua
arXiv:2602.00827v2 Announce Type: replace Abstract: Feature learning strength (FLS), i.e., the inverse of the effective output scaling of a model, plays a critical role in shaping the optimization dyn
arXiv:2605.27255v1 Announce Type: cross Abstract: Long chain-of-thought reasoning has made autoregressive decoding the dominant inference cost of modern large language models. Existing methods target
arXiv:2605.27336v1 Announce Type: new Abstract: Video Diffusion Transformers (DiTs) generate high-quality videos but demand substantial compute due to wide blocks, deep architectures, and iterative sa
arXiv:2605.26886v1 Announce Type: cross Abstract: Learning-augmented algorithms have received significant attention in recent years, particularly in the context of online optimization. Motivated by th
arXiv:2510.10774v3 Announce Type: replace-cross Abstract: Persian remains substantially underrepresented in open speech-text resources, limiting progress in multi-speaker text-to-speech (TTS), speech-
arXiv:2605.26821v1 Announce Type: cross Abstract: The Lund plane offers a physics-motivated, hierarchical representation of QCD radiation within jets, while transformer-based taggers have reached stat
arXiv:2605.26978v1 Announce Type: new Abstract: Text-to-speech (TTS) evaluation for low-resource non-Latin-script languages can fail when it relies on a single ASR round-trip word error rate (WER). A
arXiv:2511.20586v4 Announce Type: replace Abstract: Trustworthiness has become a key requirement for the deployment of artificial intelligence systems in safety-critical applications. Conventional eva
arXiv:2605.26802v1 Announce Type: new Abstract: Generating high-fidelity synthetic tabular data under formal differential privacy guarantees remains an open challenge. Methods that provide strong theo
arXiv:2605.26833v1 Announce Type: cross Abstract: Polymers underpin applications across energy, healthcare, and materials science, yet their vast chemical space makes systematic discovery challenging.
arXiv:2506.00250v4 Announce Type: replace Abstract: Large Language Models (LLMs) have achieved remarkable performance on a wide range of Natural Language Processing (NLP) benchmarks, often surpassing
arXiv:2605.26870v1 Announce Type: cross Abstract: Background: Large language models are typically evaluated as models, benchmarks, or short conversational episodes. Less is known about what happens wh
arXiv:2605.27015v1 Announce Type: new Abstract: Despite impressive multilingual capabilities, large language models (LLMs) remain poorly evaluated on literary knowledge in non-English languages. We in
arXiv:2602.03545v2 Announce Type: replace Abstract: Evaluating AI systems that interact with humans requires understanding their behavior across diverse user populations, but collecting representative
arXiv:2602.17003v2 Announce Type: replace-cross Abstract: Large language models have advanced web agents, yet current agents lack personalization capabilities. Since users rarely specify every detail
arXiv:2605.26353v1 Announce Type: cross Abstract: Different visual patterns appear with different frequencies in the world: e.g., beach balls appear on sand more often than they do on a road. These st
arXiv:2605.26256v1 Announce Type: new Abstract: Multimodal large language model (MLLM)-based embodied agents have shown strong potential for solving complex tasks in physical environments. However, pe
arXiv:2603.01800v2 Announce Type: replace-cross Abstract: Heavy-tailed distributions are ubiquitous in real-world data, where rare but extreme events dominate risk and variability. However, standard V
arXiv:2602.20475v2 Announce Type: replace-cross Abstract: The High-Luminosity Large Hadron Collider (HL-LHC) at CERN will produce unprecedented datasets capable of revealing fundamental properties of
arXiv:2605.26284v1 Announce Type: new Abstract: Accurately estimating object mass and friction is fundamental to achieving reliable and adaptive robotic manipulation. Although interactive perception p
arXiv:2507.13428v3 Announce Type: replace-cross Abstract: Video generation models have achieved remarkable progress in creating high-quality, photorealistic content. However, their ability to accurate