Search: “routing”

arXiv:2609.23979v1 Announce Type: cross Abstract: Attention encoder-decoder (AED) Speech Foundation Models achieve strong ASR performance but can generate acoustically unsupported text when inputs con

arXiv:2609.05019v1 Announce Type: new Abstract: Agents tend to optimize, select, or constrain execution structures before decisive runtime outcomes are observed. However, such pre-execution commitment

arXiv:2608.25277v1 Announce Type: new Abstract: Multi-agent LLM systems coordinate through natural-language messages that consume 40--60% of their token budget. Replacing these with structured graphs

arXiv:2608.15213v1 Announce Type: new Abstract: Crowd counting must recover reliable local density under severe variations in perspective, head scale, occlusion, and background clutter. Although moder

arXiv:2608.04183v1 Announce Type: new Abstract: When a language model follows an in-context conditional rule such as 'if P(x) then A else B,' does it assemble a runtime circuit with one module that te

arXiv:2608.03341v1 Announce Type: cross Abstract: Large language models (LLMs) have substantially improved code generation, yet achieving strong functional correctness remains difficult, especially fo

arXiv:2607.29188v1 Announce Type: new Abstract: Migrants traversing geographically distinct routes such as the Trans-Saharan and Balkan corridors often recount strikingly parallel lived experiences: p

arXiv:2607.29033v1 Announce Type: new Abstract: Existing methods for adapting 2D foundation models such as SAM to 3D volumes either process slices independently---ignoring inter-slice context---or req

arXiv:2607.29285v1 Announce Type: new Abstract: Action chunking shortens the effective decision horizon of robot imitation learning by predicting multiple future actions, while conventional phase cond

arXiv:2607.21787v1 Announce Type: new Abstract: Medical ultrasound (US) image segmentation faces significant challenges due to speckle noise, low-contrast boundaries, acoustic shadowing, and acquisiti

arXiv:2607.01426v1 Announce Type: new Abstract: Autonomous customer-service agents are shifting from conversational interfaces toward operational execution roles: they retrieve firm records, apply ser

arXiv:2605.24481v2 Announce Type: replace Abstract: The 1st Cross-Domain EgoCross Challenge at EgoVis, CVPR 2026 evaluates whether multimodal large language models can reason over egocentric videos ac

arXiv:2605.23696v1 Announce Type: new Abstract: Effectively managing Air Traffic Control Officer (ATCO) workload is crucial in maintaining operational safety. Group supervisors use tools that estimate

arXiv:2602.18600v3 Announce Type: replace Abstract: Systematic evaluation of Multimodal Large Language Models (MLLMs) is crucial for advancing Artificial General Intelligence (AGI). However, existing

arXiv:2603.26815v2 Announce Type: replace-cross Abstract: Retrieval-Augmented Generation (RAG) systems for financial document question answering typically follow a chunk-based paradigm: documents are

arXiv:2604.08868v1 Announce Type: cross Abstract: To ensure safe clinical integration, deep learning models must provide more than just high accuracy; they require dependable uncertainty quantificatio

arXiv:2610.12355v1 Announce Type: cross Abstract: Spatial reasoning remains a persistent weakness of vision-language models (VLMs), because RGB inputs do not directly provide geometric evidence. Exist

arXiv:2610.02907v1 Announce Type: new Abstract: Residual networks execute every block for every input, yet their functional contributions need not be input independent. We formulate a trained ResNet a

arXiv:2609.39892v1 Announce Type: new Abstract: Looped Transformers repeatedly apply the same set of Transformer layers, giving them a recurrent architecture for latent computation. Their strong perfo

arXiv:2609.36601v1 Announce Type: new Abstract: On-policy distillation (OPD) reduces train-test state mismatch by training a student on its own generated trajectories, but weak students may visit teac

arXiv:2609.34163v1 Announce Type: new Abstract: Vision-language navigation (VLN) is typically evaluated as a one-way task, although deployed robots may need to return after reaching a goal. We study c

arXiv:2609.29803v1 Announce Type: cross Abstract: Search quality evaluation provides essential supervision and diagnostic signals for the development and iteration of industrial search systems. Althou

arXiv:2609.09606v1 Announce Type: new Abstract: Neural radiance fields (NeRFs) and 3D Gaussian Splatting (3DGS) encode a scene with complementary inductive biases, but existing cross-representation di

arXiv:2609.08337v1 Announce Type: new Abstract: On-policy distillation (OPD) transfers teacher knowledge on student-generated trajectories, but efficient sampled objectives reduce the teacher distribu

arXiv:2606.14551v3 Announce Type: replace-cross Abstract: Robots under autonomous operation may require decisions based on evidence that is no longer visible. We study delayed-evidence tasks, where an

arXiv:2608.26743v1 Announce Type: new Abstract: Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selecti

arXiv:2608.25261v1 Announce Type: cross Abstract: Mixture-of-experts (MoE) models combine specialized predictors under learned routing, offering a principled mechanism for leveraging heterogeneity in

arXiv:2608.22034v1 Announce Type: new Abstract: Mechanistic interpretability has identified transformer circuits, but lacks a shared vocabulary for describing how their functions compose across tasks

arXiv:2608.12435v1 Announce Type: new Abstract: Transformers owe much of their strong long-context retrieval capability to a token-level memory that grows with context length. This flexibility, howeve

arXiv:2608.10470v1 Announce Type: new Abstract: Fair representation learning with a continuous sensitive attribute S requires a representation Z that is statistically independent of S. Existing criter

arXiv:2607.00064v1 Announce Type: new Abstract: As technology advances, many path-planning algorithms have been proposed for Air Traffic Management, yet their operational adoption in tactical control

arXiv:2606.23698v1 Announce Type: cross Abstract: NVIDIA's Blackwell Ultra (B300) cuts FP64 vector throughput to ~1.3 TFLOPS per GPU, roughly 30x below B200 and well below the level at which bandwidth

arXiv:2606.20970v1 Announce Type: new Abstract: Omni-modal models can ingest video, audio, and text, but unified access to multiple modalities does not guarantee that a model uses the right evidence.

arXiv:2605.25360v1 Announce Type: new Abstract: Large language models~(LLMs) are trained on heterogeneous multilingual corpora, yet existing policy optimization methods often implicitly restrict each

arXiv:2605.10194v1 Announce Type: new Abstract: On-policy self-distillation (self-OPD) densifies reinforcement learning with verifiable rewards (RLVR) by letting a policy teach itself under privileged

arXiv:2610.21320v1 Announce Type: cross Abstract: Detailed captions transfer visual information into vision-language model supervision, but quality is easily conflated with length: long single-pass ou

arXiv:2610.14061v1 Announce Type: new Abstract: State-of-the-art perceptive humanoid locomotion is mostly built on retargeted motion capture, a generative motion prior, and a distillation stage. We re

arXiv:2609.39955v1 Announce Type: new Abstract: Single-step retrosynthesis models are commonly evaluated by their ability to recover recorded reactions. In practice, chemists may need to choose among

arXiv:2609.24417v1 Announce Type: new Abstract: Despite advances in long-context inference, large language models (LLMs) remain fundamentally limited by the key-value (KV) caching mechanisms that are

arXiv:2609.19873v1 Announce Type: new Abstract: Email spam and phishing attacks remain a critical security threat. Adversaries increasingly exploit large language models to craft contextually convinci

arXiv:2609.17886v1 Announce Type: new Abstract: EEG decoding tasks can rely on different temporal dynamics and cross-channel relationships. We test whether specialized modules improve a fully fine-tun

arXiv:2608.28455v1 Announce Type: new Abstract: Contrastive vision-language learning uses paired chest CT volumes and radiology reports to learn abnormality classifiers without manually annotated labe

arXiv:2608.17914v1 Announce Type: new Abstract: Static Timing Analysis (STA) is a critical step in the design flow of digital integrated circuits, however, obtaining accurate delay estimations can rep

arXiv:2608.13463v1 Announce Type: cross Abstract: Modern image classification models excel when trained on single task-specific datasets but often struggle to generalize across domains and difficulty

arXiv:2608.03353v1 Announce Type: cross Abstract: For a Markov kernel T with an invariant probability measure pi, we give a self-contained proof of the Markov chain convergence theorem via a criterion

arXiv:2608.01751v1 Announce Type: new Abstract: Geospatial foundation models (GeoFMs), pretrained on large-scale geospatial data such as Earth observation (EO), climate, and weather data, have shown p