Content-Based Addressing for Long Context
arXiv:2609.07314v1 Announce Type: cross Abstract: Rotary position embedding (RoPE) uses each token's integer position to determine the rotation applied inside attention. This works well for local toke
Knowledge catalogue
arXiv:2609.07314v1 Announce Type: cross Abstract: Rotary position embedding (RoPE) uses each token's integer position to determine the rotation applied inside attention. This works well for local toke
arXiv:1706.04580v3 Announce Type: replace Abstract: The design and organization of complex robotic systems traditionally requires laborious trial-and-error processes to ensure both hardware and softwa
arXiv:2609.06852v1 Announce Type: new Abstract: Although highly effective in vision and language domains, applying in-context learning to robotics remains challenging. Existing autoregressive in-conte
arXiv:2609.06880v1 Announce Type: new Abstract: Reasoning over language instructions in embodied tasks such as robotics often requires understanding spatial relations from a speaker's situated perspec
arXiv:2503.15895v2 Announce Type: replace Abstract: This paper investigates whether sequential context improves goal-conditioned Reinforcement Learning in sparse-reward manipulation tasks. While Hinds
arXiv:2609.06986v1 Announce Type: new Abstract: Language models may need to internalize information that arrives over time and retain it through many subsequent updates. To study this challenge, we in
arXiv:2601.22475v2 Announce Type: replace Abstract: Building a generalist robot policy requires continuously integrating new skills while preserving previously acquired behaviors. Directly optimizing
arXiv:2609.07070v1 Announce Type: new Abstract: Spatio-temporal context has become increasingly crucial for visual tracking. However, most existing approaches extract spatio-temporal cues via discrete
arXiv:2609.05520v1 Announce Type: new Abstract: In this paper, we tackle automatic anomaly detection in multi-illumination and multi-focus display images. The minute defects on the display surface are
arXiv:2505.20498v3 Announce Type: replace Abstract: Vision-based tactile sensing is widely used in perception, reconstruction, and robotic manipulation, yet collecting large-scale tactile data remains
arXiv:2609.08660v1 Announce Type: new Abstract: Semantic segmentation on very-high-resolution images remains challenging due to the high computational cost and the difficulty of capturing fine-grained
arXiv:2609.05816v1 Announce Type: new Abstract: Crack segmentation requires a model to recognize target semantics while accurately recovering thin, low-contrast, and topologically continuous local str
arXiv:2609.07529v1 Announce Type: new Abstract: Tool-augmented language agents are vulnerable to indirect prompt injection (IPI). Unlike direct prompt injection, IPI hides adversarial instructions in
arXiv:2609.08914v1 Announce Type: new Abstract: Pixel-level annotation of fixed traffic-camera imagery is expensive, while crosswalk models trained from street-level imagery face a substantial viewpoi
arXiv:2609.07498v1 Announce Type: cross Abstract: Transferring human hand demonstrations to robotic grippers has recently emerged as a cost-effective solution for robot learning. However, existing met
arXiv:2606.19376v2 Announce Type: replace Abstract: Inference costs for large language model (LLM) applications are rapidly growing, driven by surging demand and rising infrastructure cost. Users expe
arXiv:2609.06140v1 Announce Type: cross Abstract: Agents can turn shared infrastructure into a channel for coordinated intrusion. The Hugging Face incident and a separate public-wiki investigation sho
arXiv:2609.06704v1 Announce Type: new Abstract: Chain-of-thought (CoT) may often look plausible, yet it may not faithfully reflect the model's decision-making process. While methods for measuring the
arXiv:2609.08345v1 Announce Type: new Abstract: Representing a 3D scene as multi-view images allows 2D VLMs to reason in 3D by reusing priors from pre-training, sidestepping the scarcity of annotated
arXiv:2609.08409v1 Announce Type: new Abstract: Surface coverage with task-redundant manipulators is challenging because each surface point may admit multiple inverse kinematics (IK) solutions, and co
arXiv:2609.05832v1 Announce Type: new Abstract: Integrating visuomotor policies or Vision-Language-Action (VLA) models with force/torque (F/T) perception has demonstrated significant progress in imita
arXiv:2609.07499v1 Announce Type: new Abstract: Training-free collaborative pipelines that integrate Vision Foundation Models such as CLIP, SAM, and DINO achieve strong open-vocabulary dense predictio
arXiv:2609.07336v1 Announce Type: new Abstract: Morphology of the sub-basal nerve plexus (SNP) reflects peripheral nerve health, and corneal confocal microscopy (CCM) provides an important means for i
arXiv:2609.07753v1 Announce Type: new Abstract: Synthetic Aperture Radar (SAR) is an important modality in a wide range of imaging applications due to its versatile, long range and near all weather op
arXiv:2609.05518v1 Announce Type: new Abstract: Despite the strong capabilities of multimodal large language models (MLLMs), their parametric knowledge remains incomplete and difficult to update, moti
arXiv:2609.07685v1 Announce Type: new Abstract: In real-world applications, pedestrian trajectory prediction models rely on inputs from detection and tracking systems. Prior trajectory prediction benc
arXiv:2609.08242v1 Announce Type: new Abstract: Vision-language models (VLMs) demonstrate strong performance across compositional reasoning benchmarks, which require reasoning over semantic perturbati
arXiv:2609.06302v1 Announce Type: new Abstract: Embodied visual tracking requires a robot not only to react to the current view, but to choose actions that preserve or recover future evidence of a mov
CUDA Toolkit 13.4 introduces Windows‑on‑Arm support and preview functional compatibility for the NVIDIA Rubin architecture (compute capability 107), enabling cross‑platform CUDA development on ARM sys
arXiv:2609.08244v1 Announce Type: new Abstract: Graph unlearning removes the influence of designated training data from a trained graph model without retraining from scratch. However, existing methods
arXiv:2609.09099v1 Announce Type: new Abstract: Curriculum learning is governed by several coupled design choices---how difficulty is defined, how examples are ordered, how much exposure each level re
arXiv:2609.05708v1 Announce Type: cross Abstract: Aggregating heterogeneous vision-language models (VLMs) can improve multimodal reasoning, but neither an individual model's confidence nor that of the
arXiv:2609.08730v1 Announce Type: new Abstract: While 3D Gaussian Splatting (3DGS) has emerged as a powerful representation for real-time novel view synthesis, rendering high-fidelity scenes often rel
Enterprise security startup Cymphony Inc. formally launched today with 30 million in funding and software that tracks what artificial intelligence agents and employees can reach inside company systems
arXiv:2609.07350v1 Announce Type: cross Abstract: Climate change is increasing the severity and unpredictability of natural disasters. In time-critical crises such as wildfires, traditional monitoring
arXiv:2510.10471v3 Announce Type: replace Abstract: Environmental perception systems are crucial for high-precision mapping and autonomous navigation, with LiDAR serving as a core sensor providing acc
arXiv:2609.05448v1 Announce Type: cross Abstract: Structured post-training pruning of transformers requires selecting complete functional units whose suppression causes limited degradation. We formula
arXiv:2609.05988v1 Announce Type: new Abstract: Recurrent reasoning models (RRMs) can solve structured problems, achieving easy-to-hard generalization through iterative computation in hidden space. Th
arXiv:2109.08813v1 Announce Type: cross Abstract: Seismic wave velocity of underground rock plays important role in detecting internal structure of the Earth. Rock physics models have long been the fo
arXiv:2609.06670v1 Announce Type: new Abstract: The In-context learning (ICL) paradigm aids large language models (LLMs) to adapt to new tasks without need for fine-tuning. However, selecting an optim
arXiv:2609.06053v1 Announce Type: new Abstract: The validation of data, such as customer and employee data, is an important task in many organizations. Errors in data can have severe consequences. For
arXiv:2609.05766v1 Announce Type: new Abstract: The dominant approach to building domain-specific pretraining corpora is to filter large web archives such as CommonCrawl. This works well for popular d
Databricks Inc. today expanded its Adaptive Instructed-Retriever search model to speed up response times for requests from artificial intelligence agents that require multiple rounds of retrieval. The
arXiv:2609.06107v1 Announce Type: new Abstract: Data policies for reinforcement learning with verifiable rewards (RLVR) determine which rollouts are used, how strongly they are weighted, and which dom
arXiv:2509.25180v3 Announce Type: replace Abstract: Existing text-to-image diffusion models excel at generating high-quality images, but face significant efficiency challenges when scaled to high reso
arXiv:2609.08711v1 Announce Type: new Abstract: We present DCLP++, a local navigation frameworkthat uses footprint clearance as the geometric basis for studying relative motion features in dynamic env
arXiv:2504.05161v2 Announce Type: replace-cross Abstract: Score estimation is the backbone of score-based generative models (SGMs), especially denoising diffusion probabilistic models (DDPMs). A key r
arXiv:2609.09119v1 Announce Type: new Abstract: Dexterous manipulation involves contact-rich and fine-grained interactions with the physical world, posing significant challenges for existing vision-la
arXiv:2609.07618v1 Announce Type: cross Abstract: Environments are increasingly populated by multiple robots performing independent tasks with limited prior knowledge of each other. Deploying such mul
arXiv:2609.06953v1 Announce Type: cross Abstract: This letter investigates a reach-avoid game involving two Attackers and one Defender, where the Attackers aim to maximize the number reaching the targ
arXiv:2609.06169v1 Announce Type: new Abstract: Suffix prediction forecasts the remaining sequence of events of a running case until completion. Most approaches rely on neural networks trained on even
arXiv:2406.08697v4 Announce Type: replace-cross Abstract: Offline reinforcement learning enables evaluation and optimization of sequential decisions from historical data, when it is not possible to de
arXiv:2512.21653v2 Announce Type: replace-cross Abstract: Speech codecs are usually optimized for waveform fidelity, allocating bits to acoustic detail that can be inferred from linguistic structure.
arXiv:2609.06444v1 Announce Type: cross Abstract: An LLM judge evaluates outputs at scale. Experts should label only where it is least sure. Its natural escalation signal conflates two uncertainties:
arXiv:2609.07756v1 Announce Type: new Abstract: Inertial confinement fusion (ICF) is a leading pathway toward clean energy, but each shot at the National Ignition Facility costs on the order of one mi
arXiv:2510.23258v2 Announce Type: replace-cross Abstract: Autonomous robotic navigation in real-world environments requires exploration to acquire environmental information as well as goal-directed na
arXiv:2609.06598v1 Announce Type: new Abstract: The optimal transport (OT) map provides a geometric transformation for aligning probability distributions and has become a useful tool in machine learni
arXiv:2609.05572v1 Announce Type: cross Abstract: We prove that every strictly positive probability distribution on ({-1,1}^n) is represented exactly by a sigmoid belief network with finite parameters
arXiv:2506.11032v2 Announce Type: replace Abstract: Convolutional Neural Networks (CNNs) are used to evaluate accelerometer and microphone data for bearing and induction motor diagnosis. A Long Short-
arXiv:2609.07180v1 Announce Type: new Abstract: Basal Cell Carcinoma (BCC) is the most common type of skin cancer, accounting for nearly 80% of skin cancer di- agnoses. Its optimal clinical management