Optical Flow from Photons
arXiv:2608.00499v1 Announce Type: new Abstract: Optical flow remains challenging in high-speed and low-light scenes, where the limited frame rate and sensitivity of conventional cameras lead to motion
Knowledge catalogue
arXiv:2608.00499v1 Announce Type: new Abstract: Optical flow remains challenging in high-speed and low-light scenes, where the limited frame rate and sensitivity of conventional cameras lead to motion
arXiv:2603.11804v3 Announce Type: replace Abstract: Vision-Language Models (VLMs) adapted to remote sensing rely heavily on domain-specific image-text supervision, yet high-quality annotations for sat
arXiv:2608.01458v1 Announce Type: new Abstract: Large language models are being extensively used to simulate individual user behavior, yet faithfully representing a population requires capturing the s
arXiv:2506.13741v2 Announce Type: replace-cross Abstract: Preference-based reinforcement learning (PbRL) has emerged as a promising approach for learning behaviors from human feedback without predefin
arXiv:2607.18361v2 Announce Type: replace Abstract: Deep neural networks have become a promising approach for IMU-based sensing, but their scalability is fundamentally limited by costly labeled data a
Picking the right agent harness is now a crucial skill for any AI engineer. Imagine using the same model, same task, and same prompt. Now move it between two agent harnesses and the cost per success c
arXiv:2608.01072v1 Announce Type: new Abstract: Autoregressive rigging models such as UniRig and SkinTokens perform well on articulated characters, but their ability to generalize to plant structures
arXiv:2608.00045v1 Announce Type: new Abstract: This study shows that textual descriptors alone can predict early-stage startup success, defined as Exit, without relying on contextual, financial, or h
arXiv:2608.01201v1 Announce Type: cross Abstract: End-to-end autonomous driving (E2E AD) systems integrate perception, prediction, and planning into a single differentiable architecture. While these m
arXiv:2608.02545v1 Announce Type: new Abstract: Reachability analysis for visuomotor policies is difficult because large visual encoders make end-to-end set propagation computationally expensive and e
arXiv:2608.01690v1 Announce Type: new Abstract: Biological wet-lab protocols are written for trained researchers and often leave routine operations, state-dependent conditions, and contextual paramete
arXiv:2608.02053v1 Announce Type: cross Abstract: Brain tissue microstructure estimation with machine learning provides higher computational efficiency than conventional fitting. However, machine lear
arXiv:2608.01422v1 Announce Type: new Abstract: Machine unlearning seeks to remove targeted information from trained models without requiring costly retraining. Existing optimization-based methods oft
arXiv:2510.14546v2 Announce Type: replace Abstract: Embeddings from Visual-Language Models are increasingly utilized to represent semantics in robotic maps, offering an open-vocabulary scene understan
arXiv:2608.01522v1 Announce Type: cross Abstract: Teaching a language model a skill it has not mastered is obstructed by three recurring difficulties: training data is scarce, ground-truth reasoning t
arXiv:2508.08645v3 Announce Type: replace Abstract: As multimodal large language models advance rapidly, the automation of mobile tasks has become increasingly feasible through the use of mobile-use a
arXiv:2608.01626v1 Announce Type: new Abstract: Short-term precipitation nowcasting is important for hydrometeorological early warning, especially when intense convective rainfall may trigger urban fl
arXiv:2602.07086v2 Announce Type: replace-cross Abstract: Enterprise software systems commonly expose business functionality through both relational databases and REST APIs. Accessing these interfaces
arXiv:2608.01301v1 Announce Type: new Abstract: Infrared-visible image fusion (IVIF) has no ideal fused reference, so fusion algorithms are routinely ranked by scalar objective metrics that formalize
arXiv:2602.02599v4 Announce Type: replace Abstract: Long-context inference in large language models (LLMs) is bottlenecked by the memory and compute of the key-value (KV) cache. Structured pruning is
arXiv:2608.00232v1 Announce Type: new Abstract: Surgical augmented reality (AR) can provide contextual guidance by overlaying virtual annotations, tool cues, and procedural information onto the surgic
arXiv:2608.01875v1 Announce Type: cross Abstract: Most time series (TS) models are specialized for a single task, either understanding (i.e., returning text answers about a TS) or generation (i.e., re
arXiv:2608.02561v1 Announce Type: new Abstract: Automated pain assessment in real clinics is limited by scarce clinically grounded facial video data with weak labels (often sequence-level self-report)
arXiv:2608.00586v1 Announce Type: new Abstract: Despite the widespread adoption of foundation models as feature extractors for medical imaging, relatively little is understood about how different pret
arXiv:2608.02316v1 Announce Type: new Abstract: State estimation is a key component in model-based control of walking robots and, more broadly, applicable wherever hidden variables must be inferred. T
arXiv:2510.21590v3 Announce Type: replace Abstract: Current image super-resolution methods show strong performance on natural images but distort text, creating a fundamental trade-off between image qu
arXiv:2608.01247v1 Announce Type: new Abstract: Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse und
arXiv:2608.00943v1 Announce Type: cross Abstract: Automated sleep staging assigns discrete stage labels to successive time epochs throughout an overnight recording; conventionally each window spans at
arXiv:2608.00135v1 Announce Type: cross Abstract: Design and architectural archives encode expert human knowledge in graphical formats, providing a critical testbed for design-inspired Machine Learnin
arXiv:2608.01824v1 Announce Type: new Abstract: Fusing tactile signals has proven effective for contact-rich manipulation, enabling robots to perceive contact states and adapt to rapidly changing phys
arXiv:2608.01468v1 Announce Type: new Abstract: This work presents DS@GT ARC BioASQ team's work for a biomedical question answering pipeline, integrating multi-source query expansion, neural reranking
arXiv:2608.01311v1 Announce Type: new Abstract: Generating long-form content from extensive internal reports remains challenging for organizations operating under strict privacy and security constrain
arXiv:2608.01630v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) improves factuality but adds latency and engineering overhead at serving time. We propose RING (Retrieval-Internali
arXiv:2608.00822v1 Announce Type: new Abstract: We present Riemannian Informed Trees (RIT*), a planning framework that replaces Euclidean primitives in batch-informed search with their Riemannian coun
arXiv:2608.00335v1 Announce Type: cross Abstract: Compact web agents can reduce deployment cost, but training them poses challenges in both data collection and post-SFT reinforcement learning (RL). Su
arXiv:2509.20717v2 Announce Type: replace Abstract: Long-horizon, high-dynamic motion tracking on humanoids remains brittle: retargeted reference motions are typically kinematically plausible but dyna
arXiv:2608.00543v1 Announce Type: cross Abstract: Although semantic watermarking is considered a promising safeguard for images generated by Latent Diffusion Models (LDMs), the reliance of the waterma
arXiv:2608.02555v1 Announce Type: new Abstract: Arabizi refers to Arabic written in Latin script. Although previous studies have shown that the prevalence and usage of Arabizi vary by factors such as
arXiv:2608.02200v1 Announce Type: new Abstract: Traffic police gestures are safety-critical perception cues for autonomous driving. A deployable recognizer must infer commands causally from continuous
arXiv:2607.09757v2 Announce Type: replace Abstract: Parameter-efficient fine-tuning enables large language models to adapt to downstream tasks with substantially lower computational and storage cost,
arXiv:2603.21611v2 Announce Type: replace Abstract: 3D fragment reassembly estimates the rigid pose of each fragment to recover a complete object from unordered point clouds or meshes. The task become
arXiv:2608.02052v1 Announce Type: new Abstract: Human mobility prediction models, which forecast the next location in a user's trajectory, are increasingly deployed in urban analytics, navigation, and
arXiv:2608.00311v1 Announce Type: new Abstract: Long-context inference with large language models (LLMs) is costly: self-attention during prefill scales quadratically with sequence length, and the key
arXiv:2510.22868v2 Announce Type: replace Abstract: Wind turbine blades operate in harsh environments, making timely damage detection essential for preventing failures and optimizing maintenance. Dron
arXiv:2608.00658v1 Announce Type: new Abstract: Retrieval-augmented generation (RAG) for language model (LM) systems fundamentally has two failure modes: retrieval failure and reading failure. The for
arXiv:2507.02778v3 Announce Type: replace Abstract: Although large language models (LLMs) have transformed AI, they still make errors and follow unproductive reasoning paths. Self-correction is vital
arXiv:2608.02208v1 Announce Type: new Abstract: Whole-body dual-energy X-ray absorptiometry (DXA) scans are routinely acquired to measure bone density and regional body composition, leaving their spat
arXiv:2608.02348v1 Announce Type: cross Abstract: Malware clustering is a critical task in cybersecurity that helps discover threats and analyze evolving malware families. While self-supervised learni
arXiv:2608.01106v1 Announce Type: new Abstract: Understanding and generating spatially coherent layouts from natural language remains a fundamental yet challenging task for large language models (LLMs
arXiv:2608.01397v1 Announce Type: cross Abstract: World Action Models (WAMs) couple action generation with prediction of future states. Their effectiveness depends on whether future dynamics are model
arXiv:2608.00246v1 Announce Type: new Abstract: Machine unlearning removes the influence of user-specified training examples from a trained model, avoiding the need to retrain it from scratch. Localiz
arXiv:2608.00872v1 Announce Type: cross Abstract: Federated Learning (FL) enables collaborative training of machine learning models across multiple institutions without sharing sensitive data, making
arXiv:2608.02571v1 Announce Type: new Abstract: Quadruped robots are a promising platform for search and rescue missions because they can navigate cluttered indoor environments that may be restrictive
arXiv:2608.00859v1 Announce Type: new Abstract: Kolmogorov--Arnold Networks (KANs) replace scalar edge weights with learnable univariate functions parameterized by multiple basis coefficients. This in
arXiv:2608.01103v1 Announce Type: new Abstract: Object-centric models often produce fragmented masks, boundary leakage, and incorrect region merging. We introduce Similarity-Shift Refinement (SSR), a
arXiv:2608.01530v1 Announce Type: new Abstract: Reliable decision-support in digital agriculture requires accurate predictions and well-calibrated uncertainty estimates, particularly for dense predict
arXiv:2608.02070v1 Announce Type: new Abstract: Brain-computer interfaces (BCIs) have been widely used in motor rehabilitation, disease diagnosis, and other neural engineering scenarios. However, conv
arXiv:2608.01024v1 Announce Type: cross Abstract: We study the problem of optimizing physical layouts for automated warehouses, where hundreds to thousands of robots are coordinated to transport packa
arXiv:2608.01954v1 Announce Type: new Abstract: Fixed-layout indoor furniture styling requires selecting assets that form a coherent room without changing the prescribed furniture categories, position
arXiv:2608.00928v1 Announce Type: new Abstract: Subtype robustness asks whether a model keeps the correct coarse prediction when test examples come from fine-grained subtypes absent from training but