Normalizing Trajectory Models
arXiv:2605.08078v1 Announce Type: new Abstract: Diffusion-based models decompose sampling into many small Gaussian denoising steps -- an assumption that breaks down when generation is compressed to a
Knowledge catalogue
arXiv:2605.08078v1 Announce Type: new Abstract: Diffusion-based models decompose sampling into many small Gaussian denoising steps -- an assumption that breaks down when generation is compressed to a
arXiv:2605.06892v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) have achieved state-of-the-art video generation quality, but they incur immense computational cost because standard infere
arXiv:2605.07828v1 Announce Type: cross Abstract: The convergence of Krylov-based linear iterative solvers applied to parametric partial differential equations (PDEs) is often highly sensitive to the
arXiv:2605.07606v1 Announce Type: cross Abstract: Detecting levels of psychological defence mechanisms in supportive conversations is inherently ambiguous. In the PsyDefDetect shared task at BioNLP 20
arXiv:2605.06835v1 Announce Type: cross Abstract: Tabular data plays an important role in many fields and industries, including those with elevated privacy considerations and risks. As such, there is
arXiv:2605.07289v1 Announce Type: cross Abstract: ReDoS is a well-known type of algorithmic complexity attack, where an adversary supplies maliciously crafted strings to a regular expression matching
arXiv:2605.06874v1 Announce Type: new Abstract: Learning rate is a critical component of reinforcement learning (RL). This work uses global and local clocks to distinguish two types of learning rates.
arXiv:2605.07220v1 Announce Type: new Abstract: Diffusion guidance is a powerful technique that enables controllable and high-fidelity sample generation with diffusion models. At a high level, it modi
arXiv:2605.06680v1 Announce Type: cross Abstract: Flow matching generates data by integrating a learned velocity field, where the number of integration steps (NFE) directly determines inference cost.
arXiv:2605.07736v1 Announce Type: new Abstract: Online goal recognition in continuous domains poses two central challenges: efficiently encoding large trajectories and effectively comparing them. Rece
arXiv:2605.05497v2 Announce Type: replace Abstract: Conformal prediction is a framework that provides valid uncertainty quantification for general models with exchangeable data. However, in the online
arXiv:2605.07649v1 Announce Type: cross Abstract: Over the last few years, research on autonomous systems has matured to such a degree that the field is increasingly well-positioned to translate resea
arXiv:2605.07695v1 Announce Type: new Abstract: High-fidelity surgical video generation can greatly improve medical training and the development of AI, adapting these generative models for precise vid
arXiv:2408.07522v2 Announce Type: replace-cross Abstract: Voice signals originating from the respiratory tract are utilized as valuable acoustic biomarkers for the diagnosis and assessment of respirat
arXiv:2602.10024v2 Announce Type: replace-cross Abstract: The principal goal of the RAG TREC Instrument for Multilingual Evaluation (RAGTIME) track at TREC is to study report generation from multiling
arXiv:2605.07584v1 Announce Type: new Abstract: Lifted classical planners operate directly on first-order planning tasks to avoid the computationally demanding grounding step. However, lifted planning
arXiv:2605.08006v1 Announce Type: cross Abstract: We study a class of bilevel optimization problems in which both the upper- and lower-level problems have minimax structures. This setting captures a b
arXiv:2605.07252v1 Announce Type: cross Abstract: Co-speech gesture generation aims to synthesize realistic body movements that are semantically coherent with speech and faithful to a user-specified g
arXiv:2605.08030v1 Announce Type: new Abstract: Positron Emission Tomography (PET) image reconstruction is inherently challenged by Poisson noise and physical degradation factors, which are further ex
arXiv:2605.06756v1 Announce Type: new Abstract: Real-time supervisory control of thermal energy distribution systems requires digital twins that are accurate, interpretable, and uncertainty-aware, yet
arXiv:2605.07738v1 Announce Type: cross Abstract: Physics-informed operator learning is an attractive candidate for surrogate modeling of microstructures, especially in multiscale finite-element simul
arXiv:2605.07188v1 Announce Type: new Abstract: We present PicoEyes, a unified gaze estimation framework that directly predicts all key attributes of gaze, including 3D eye parameters, eye-region segm
arXiv:2605.07215v1 Announce Type: new Abstract: Stochastic trajectory optimization methods like STOMP enable planning with non-differentiable costs, offering substantial flexibility over gradient-base
arXiv:2605.07067v1 Announce Type: new Abstract: Muon's matrix-level update couples two distinct effects: spectral control via a polar map, and equivariance under orthogonal changes of multiplicity-spa
arXiv:2605.07796v1 Announce Type: new Abstract: SQL dialects vary in syntax, types, and functions across database engines. Text-to-SQL benchmarks, however, predominantly support only SQLite. This crea
arXiv:2605.07838v1 Announce Type: cross Abstract: Understanding how molecular alterations propagate across biological systems to drive disease remains a central challenge. Although high-throughput pro
arXiv:2605.07765v1 Announce Type: new Abstract: In this work, we study TabPFN as a training-free, modular summary network for simulation-based Bayesian inference (SBI). Tabular foundation models such
arXiv:2605.07810v1 Announce Type: cross Abstract: Optical neural networks are emerging as powerful machine learning and information processing tools because of their potential advantages in speed and
arXiv:2603.00223v2 Announce Type: replace Abstract: We investigate a quantum-inspired approach to supervised multi-class classification based on the Pretty Good Measurement (PGM), viewed as an operato
arXiv:2510.00322v3 Announce Type: replace-cross Abstract: Standard techniques for differentially private estimation, such as Laplace or Gaussian noise addition, require guaranteed bounds on the sensit
arXiv:2605.07554v1 Announce Type: cross Abstract: Protein language models are trained primarily with masked language modeling (MLM), which predicts amino-acid identities at masked positions. We ask wh
arXiv:2605.06830v1 Announce Type: cross Abstract: Protein language models (pLMs) produce per-residue representations that capture evolutionary and structural information, yet their mean-pooled sequenc
arXiv:2605.07375v1 Announce Type: new Abstract: Normalization layers in neural operators usually compute statistics by uniformly averaging discrete grid values, making the normalization itself discret
arXiv:2605.06758v1 Announce Type: cross Abstract: Relative spatial relations provide a compact representation of spatial structure and are fundamental to relative spatial reasoning in 3D layout genera
arXiv:2605.07945v1 Announce Type: new Abstract: We present CoopNet, an approach that improves the cooperation of co-trained networks by dynamically adapting the apportionment of gradient, to ensure eq
arXiv:2605.07155v1 Announce Type: new Abstract: Agnostic online learning is classically solved via a reduction to the realizable setting, utilizing Littlestone's Standard Optimal Algorithm (SOA) as a
arXiv:2605.06914v1 Announce Type: cross Abstract: Recent methods expose intra-request parallelism in LLM outputs, allowing independent branches to decode concurrently. Existing serving systems execute
arXiv:2605.06055v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) inference requires large-scale token exchange across devices, making dispatch and combine major bottlenecks in both p
arXiv:2605.07654v1 Announce Type: cross Abstract: Large Language Models often improve accuracy on reasoning tasks by sampling multiple Chain-of-Thought (CoT) traces and aggregating them with majority
arXiv:2605.07307v1 Announce Type: new Abstract: Modern reasoning language models generate dense, sequential chain-of-thought traces implicitly assuming that every token contributes and that steps must
arXiv:2605.07164v1 Announce Type: new Abstract: Self-evolving agents improve by accumulating and reusing experience from past interactions. Existing work has largely focused on how experience is const
arXiv:2605.05806v2 Announce Type: replace Abstract: Retrieval-augmented generation (RAG) typically treats retrieval and generation as separate systems. We ask whether an attention-based encoder-decode
arXiv:2602.11162v2 Announce Type: replace Abstract: Recent studies have identified 'retrieval heads' in Large Language Models (LLMs) responsible for extracting information from input contexts. However
arXiv:2605.07106v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have made remarkable progress on vision-language reasoning, yet most methods still compress visual evidence int
arXiv:2605.06764v1 Announce Type: cross Abstract: Learning from a sequence of interactions, as soon as observations are perceived and acted upon, without explicitly storing them, holds the promise of
arXiv:2602.19974v2 Announce Type: replace Abstract: Recent advancements in image generation have achieved impressive results in producing high-quality images. However, existing image generation models
arXiv:2605.07634v1 Announce Type: cross Abstract: We consider a first order stochastic optimization framework where, at each iteration, K independent identically distributed (i.i.d.) data point sample
arXiv:2605.05693v2 Announce Type: replace Abstract: Post-training quantization (PTQ) is an effective approach for deploying large language models (LLMs) under memory and latency constraints. Most exis
arXiv:2605.07604v1 Announce Type: cross Abstract: 3D animal reconstruction in the wild remains challenging due to large species variation, frequent occlusions, and the prevalence of multi-animal scene
arXiv:2605.07239v1 Announce Type: new Abstract: We establish sample complexity results for stochastic optimization over the integers, especially with a view to understand the complexity with respect t
arXiv:2511.16520v2 Announce Type: replace-cross Abstract: Foundation flow-matching (FM) models promise a universal prior for solving inverse problems (IPs), yet today they trail behind domain-specific
arXiv:2508.15989v2 Announce Type: replace Abstract: Equilibrium Propagation (EP) is a biologically inspired local learning rule first proposed for convergent recurrent neural networks (CRNNs), in whic
arXiv:2509.00338v3 Announce Type: replace-cross Abstract: Hierarchical reinforcement learning (RL) has the potential to enable effective decision-making over long timescales. Existing approaches, whil
arXiv:2602.03473v2 Announce Type: replace-cross Abstract: Continual learning, especially class-incremental learning (CIL), on the basis of a pre-trained model (PTM) has garnered substantial research i
arXiv:2605.07465v1 Announce Type: new Abstract: Instruction following is a fundamental capability of large language models (LLMs), yet continuously improving this capability remains challenging. Exist
arXiv:2605.07076v1 Announce Type: new Abstract: Large language models (LLMs) increasingly receive information as streams of passages, conversations, and long-context workflows. While longer context wi
arXiv:2605.06730v1 Announce Type: new Abstract: We introduce Semantic State Abstraction Interfaces (SSAI): a methodological template for mapping sparse unstructured text into K auditable, named coordi
arXiv:2605.08034v1 Announce Type: cross Abstract: Distributional treatment effects can be invisible to means: a treatment may preserve average outcomes while changing tails, modes, dispersion, or rare
arXiv:2605.07531v1 Announce Type: new Abstract: Black-Box Variational Inference (BBVI) typically relies on Stochastic Gradient Descent (SGD) to optimize the Evidence Lower Bound (ELBO). However, the s
arXiv:2603.24914v2 Announce Type: replace-cross Abstract: Artificial intelligence is transforming mathematics at a speed and scale that demand active engagement from the mathematical community. We exa