Search: “routing”

arXiv:2605.26678v1 Announce Type: new Abstract: Long-context language models are limited by the memory footprint of the key-value (KV) cache. Existing training-free KV compression methods usually rank

arXiv:2605.27220v1 Announce Type: new Abstract: In modern RAG pipelines, query augmentation methods such as HyDE and query expansion are applied to every query, resulting in substantial LLM inference

arXiv:2605.25893v1 Announce Type: new Abstract: Despite the emergence of diffusion large language models (D-LLMs) as an alternative to autoregressive large language models (AR-LLMs), safety monitoring

arXiv:2605.21994v1 Announce Type: new Abstract: GraphRAG conditions language models on subgraphs retrieved from knowledge graphs, encoded via message-passing GNNs. Because these encoders entangle node

arXiv:2602.06025v2 Announce Type: replace Abstract: Memory is increasingly central to Large Language Model (LLM) agents operating beyond a single context window, yet most existing systems rely on offl

arXiv:2605.20667v1 Announce Type: new Abstract: Detecting small unmanned aerial vehicles from RGB-infrared remote-sensing pairs remains challenging due to tiny target scale, cluttered backgrounds, and

arXiv:2602.06862v2 Announce Type: replace Abstract: Adapting pre-trained vision models using parameter-efficient fine-tuning (PEFT) remains challenging, as it aims to achieve performance comparable to

arXiv:2605.21121v1 Announce Type: new Abstract: Single-image-to-3D generative models can now produce high-quality geometry, yet conditioning on a single view inevitably introduces ambiguity about unse

arXiv:2601.09512v2 Announce Type: replace-cross Abstract: To teach robots complex manipulation tasks, a common approach is to fine-tune a pre-trained vision-language-action model (VLA) on task-specifi

arXiv:2508.17218v3 Announce Type: replace-cross Abstract: Reliable path planning in stochastic transportation networks requires decisions that account for uncertain and correlated travel times on irre

arXiv:2605.14438v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures enhance the efficiency of large language models by activating only a subset of experts per token. However, standa

arXiv:2602.02711v2 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance in long-horizon decision-making tasks through multi-step interaction and reasoning at test t

arXiv:2605.11153v1 Announce Type: new Abstract: We decompose an evolutionary mixture-of-LoRA system on a from-scratch ~150M-parameter widened-D substrate (D=1536, V=32000; D/V approx 0.048; the 'widen

arXiv:2605.09802v1 Announce Type: cross Abstract: Vision-language models (VLMs) enable text-guided object detection but degrade severely under cross-view scenarios where ground and aerial viewpoints d

arXiv:2604.00754v2 Announce Type: replace Abstract: The whole-brain connectome of a fruit fly comprises over 130K neurons connected with a probability of merely 0.02%, yet achieves an average shortest

arXiv:2605.00336v1 Announce Type: new Abstract: A key challenge for large language models is token cost per query and overall deployment cost. Clinical inputs are long, heterogeneous, and often redund

arXiv:2605.00356v1 Announce Type: new Abstract: Long-term conversational agents must decide which turns to store in external memory, yet recent systems rely on autoregressive LLM generation at every t

arXiv:2604.26644v1 Announce Type: new Abstract: Large Reasoning Models (LRMs) achieve strong performance on mathematical reasoning tasks but remain unreliable on challenging instances. Existing test-t

arXiv:2604.24428v1 Announce Type: cross Abstract: Electroencephalography (EEG) is highly susceptible to artifact contamination, such as electrooculographic (EOG) and electromyographic (EMG) interferen

arXiv:2604.22885v1 Announce Type: cross Abstract: Federated cross-modal retrieval faces severe challenges from heterogeneous client data, particularly non-IID semantic distributions and missing modali

arXiv:2604.22808v1 Announce Type: cross Abstract: Long-sequence video diffusion transformers hit a quadratic self-attention cost that dominates runtime and memory for very long token sequences. Most e

arXiv:2604.23530v1 Announce Type: cross Abstract: Multi-turn, long-horizon tasks are increasingly common for large language models (LLMs), but solving them typically requires many sequential model inv

arXiv:2602.13211v2 Announce Type: replace-cross Abstract: Compared with IP multicast, Overlay Multicast (OM) offers better compatibility and flexible deployment in heterogeneous, cross-domain networks

arXiv:2604.21029v1 Announce Type: cross Abstract: The recent emergence of planar transport systems necessitates re-evaluation of Flexible Manufacturing Systems (FMS) to address the simultaneous schedu

arXiv:2604.13414v1 Announce Type: new Abstract: Majority-vote ensembles achieve variance reduction by averaging over diverse, approximately independent base learners. When training data exhibits Marko

arXiv:2604.13517v1 Announce Type: new Abstract: Temporal credit assignment in reinforcement learning has long been a central challenge. Inspired by the multi-timescale encoding of the dopamine system

arXiv:2604.00136v2 Announce Type: replace-cross Abstract: Multi-model LLM serving operates in a non-stationary, noisy environment: providers revise pricing, model quality can shift or regress without

arXiv:2604.12257v1 Announce Type: new Abstract: Underwater Image Enhancement (UIE) is essential for robust visual perception in marine applications. However, existing methods predominantly rely on uni

arXiv:2602.22918v2 Announce Type: replace Abstract: Vision-language models (VLMs) can read text from images, but where does this optical character recognition (OCR) information enter the language proc

Harrison Chase, co-founder of LangChain, argues that while prompt engineering is foundational and can get you 80% of the way to a functional AI system, the remaining 20% of engineering effort involves

arXiv:2610.14710v1 Announce Type: new Abstract: Large Language Models (LLMs) have shown strong potential for text-attributed graph learning by leveraging rich pre-trained knowledge and language unders

arXiv:2610.03240v1 Announce Type: new Abstract: Large language models (LLMs) are increasingly deployed in public health, finance, and governance, requiring both accuracy and societal value alignment.

arXiv:2610.01418v1 Announce Type: new Abstract: Spiking Neural Networks (SNNs) enable event-driven computation through biologically inspired dynamics at the neuronal scale, while Mixture-of-Experts (M

arXiv:2609.38246v1 Announce Type: cross Abstract: Deepfakes no longer need to fake a whole video. Generators that read the transcript now alter only the few seconds in which a video's meaning turns, s

arXiv:2609.33340v1 Announce Type: new Abstract: Contextual specialization can improve forecasting accuracy, but a correction selected on one historical interval may become unreliable under temporal di

arXiv:2609.30667v1 Announce Type: new Abstract: A robust world model must strike the balance between faithfully capturing environmental dynamics and abstracting away from irrelevant content. While rec

arXiv:2609.28919v1 Announce Type: new Abstract: Harnesses, the products that run AI coding agents, are multiplying, and enterprises are rolling them out to their employees: what started as pilots with

arXiv:2609.29715v1 Announce Type: cross Abstract: Surrogate models are often chosen during development and then left in place as new measurements arrive. That practice becomes risky when noise, input

arXiv:2609.25039v1 Announce Type: cross Abstract: Entropy over chain-of-thought tokens decides which tokens receive the policy gradient, which get pruned, and whether a run has collapsed, yet each suc

arXiv:2609.23164v1 Announce Type: cross Abstract: Vinyl restoration systems must distinguish isolated clicks, short bursts, dense crackle, and overlapping damage before selecting a repair operation. W

arXiv:2609.17564v1 Announce Type: new Abstract: Deploying retrieval-augmented generation (RAG) on commodity GPUs such as the NVIDIA T4 (16 GB VRAM) exposes a practical failure mode we call the Compres

arXiv:2609.18672v1 Announce Type: new Abstract: An AI assistant that calls tools makes two decisions on every request: which tool to invoke, and whether any available tool applies. In the usual design

arXiv:2609.14288v1 Announce Type: new Abstract: Large language models increasingly analyze computational results and draft manuscripts, making reliable communication as important as correct analysis.

arXiv:2609.13901v1 Announce Type: cross Abstract: Multi-charger scheduling in wireless rechargeable sensor networks must weigh sensor death risk, charger energy, travel cost, return-to-base feasibilit

arXiv:2609.11899v1 Announce Type: new Abstract: Long-video understanding on edge devices must reason over hours of content under tight compute and bandwidth budgets. Subsampling visual tokens loses te

arXiv:2609.11355v1 Announce Type: new Abstract: This paper describes our system for Task~2 of the second Multilingual Conversational Speech Language Model (MLC-SLM) Challenge. We adapt Qwen3-Omni-30B-