Search: “routing”

arXiv:2606.23181v2 Announce Type: replace Abstract: Hybrid reasoning models can answer directly or spend extra tokens on extended thinking. A practical router should choose between these modes for eac

arXiv:2608.28697v1 Announce Type: new Abstract: Additive manufacturing (AM) enables compact hydraulic components whose internal fluid channels can follow free-form 3D paths rather than conventionally

arXiv:2601.21545v2 Announce Type: replace Abstract: Agentic systems accumulate persistent memory across sessions, tools, and tasks, and a later request must retrieve from it under two distinct constra

arXiv:2608.24112v1 Announce Type: new Abstract: Modern text-to-image (T2I) models often have similar total scores but different strengths, making practical selection difficult. Fine-grained benchmarks

arXiv:2608.21762v1 Announce Type: cross Abstract: Vision-language models (VLMs) fail many detail-centric questions for a concrete reason: the answer is visible in the image, yet lost after the image i

arXiv:2608.21375v1 Announce Type: new Abstract: Heterogeneous agentic retrieval-augmented generation (RAG) systems increasingly orchestrate external APIs, internal databases, vector stores, and graph

arXiv:2608.21278v1 Announce Type: new Abstract: Improving the safety of large language models (LLMs) often comes at the expense of utility, as globally applied safety tuning may affect model responses

arXiv:2608.14927v1 Announce Type: new Abstract: Multi-agent large language model (LLM) systems can improve reasoning by spending more computation, but deployment requires deciding when extra collabora

arXiv:2608.14641v1 Announce Type: new Abstract: Agentic systems increasingly delegate model selection to a router, yet open-source routers are usually evaluated with different tasks, candidate pools,

arXiv:2608.16810v1 Announce Type: new Abstract: Identifying and representing object instances such as cells or nuclei is a common task in microscopy image analysis. Established machine learning workfl

DeepSeek V4 Pro 0813 and Claude Fable 5 were benchmarked on DeepSWE. A cascading strategy that starts with Pro 0813 and escalates to Fable only when it fails solves 82.7 % of tasks at an average cost

arXiv:2608.12715v1 Announce Type: cross Abstract: Generative speech enhancement faces three gaps: spectral models capture harmonic structure but often disrupt phase, waveform models preserve phase but

arXiv:2608.13478v1 Announce Type: new Abstract: We present our submission to Task 3 of the Genmu 2.0 Challenge on visual concept unlearning. Building on MapRoute, we introduce task-specific training o

arXiv:2608.11785v1 Announce Type: new Abstract: Large language models (LLMs) have shown strong potential for financial analysis and trading, but direct trading remains challenging because the predicti

arXiv:2608.08853v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) routers commonly use the same scores both to select experts and to weight their already-computed outputs. We study wheth

arXiv:2608.09907v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have shown strong multimodal instruction-following ability, but adapting them to diverse visual-language domain

arXiv:2608.07922v1 Announce Type: new Abstract: Adaptive learning needs both a state that preserves what observations imply and opportunities to act on that state. We study this width--depth tradeoff

arXiv:2608.08889v1 Announce Type: new Abstract: Recommendation systems thrive on personalization, where ''correctness'' is rarely a binary truth but a matter of subjective human preference. As Large L

arXiv:2608.04956v1 Announce Type: new Abstract: Recent video models increasingly support generation, reference conditioning, and editing within a single model, yet typically expose them as separate op

arXiv:2608.03902v1 Announce Type: new Abstract: Resource constraints on UAV platforms have driven a paradigm shift in aerial tracking, from pursuing performance toward balancing accuracy with efficien

arXiv:2608.00970v1 Announce Type: new Abstract: Object-oriented aerial vision-and-language navigation (VLN) requires searching for a described target and landing on it precisely, under long-horizon an

arXiv:2607.28991v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have demonstrated remarkable capabilities in multimodal understanding and generation. However, when textual inp

arXiv:2607.29545v1 Announce Type: new Abstract: Multimodal video generation aims to generate and edit videos conditioned on arbitrary combinations of text, images, and videos within a single model, al

arXiv:2607.27289v1 Announce Type: new Abstract: The promise of multimodal fusion lies in combining complementary sources of evidence, yet more evidence does not always yield a better prediction. Recen

arXiv:2607.25357v1 Announce Type: cross Abstract: Long-context recall in linear-time sequence models highlights a tradeoff in how they write to memory. State-based linear models, such as state-space m

arXiv:2607.25422v1 Announce Type: new Abstract: Knowledge-intensive multimodal question answering (KI-MMQA) sits at the intersection of three expensive primitives: long visual token sequences, dense r

arXiv:2607.23657v1 Announce Type: new Abstract: Articulated portrait mesh estimation is fundamental to 3D understanding, avatar generation, and immersive interaction. Existing approaches primarily rel

arXiv:2607.13187v1 Announce Type: new Abstract: Face identification has achieved remarkable performance under normal conditions. Yet, its accuracy often degrades significantly when query faces are par

arXiv:2607.14041v1 Announce Type: cross Abstract: Historical Manchu OCR must accommodate various visually distinct writing styles, including regular script, running script, and the semi-cursive chance

arXiv:2607.13594v1 Announce Type: new Abstract: LLM agents act on real-world environments through tool calls, and a single misjudged action can cause irreversible harm. The standard safeguard is a gua

arXiv:2607.03693v1 Announce Type: new Abstract: Vision-language-action (VLA) models have advanced generalist robotic manipulation, yet real-world deployment reveals a fundamental challenge: robots are

arXiv:2511.02200v2 Announce Type: replace Abstract: The emergence of multi-agent systems powered by large language models (LLMs) has unlocked new frontiers in complex task-solving, enabling diverse ag

arXiv:2607.05093v1 Announce Type: new Abstract: The exponential growth of video traffic demands novel semantic communication paradigms that transmit meaning rather than raw bits. We present a generati

arXiv:2603.08982v2 Announce Type: replace Abstract: Diffusion Transformers (DiTs) have become a leading backbone for video generation, yet their quadratic attention cost remains a major bottleneck. Sp

arXiv:2606.30030v1 Announce Type: new Abstract: Blind image deblurring demands the recovery of high-fidelity details and coherent structures from complex, unknown degradations. Current blind image deb

arXiv:2606.30345v1 Announce Type: cross Abstract: Enabling large language models to achieve stable self-improvement without external expert supervision remains a central challenge in complex reasoning

arXiv:2606.23041v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) have achieved remarkable success in visual understanding but remain constrained in visual generation due to the

arXiv:2606.09811v1 Announce Type: cross Abstract: World-action models have emerged as a promising paradigm for robot manipulation, jointly modeling visual scene dynamics and actions to inject physical

arXiv:2606.06219v1 Announce Type: new Abstract: End-to-end autonomous driving models often struggle to balance multi-modal maneuver generation with real-time inference constraints. While diffusion mod

arXiv:2606.04816v1 Announce Type: new Abstract: Large language models (LLMs) increasingly translate natural-language optimization problems into executable solver code. Yet for constraint-dense operati

arXiv:2606.02581v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) faces a fundamental three-way tension: deeper retrieval improves factual grounding but inflates token costs and e

arXiv:2509.22854v2 Announce Type: replace Abstract: Implicit in-context learning (ICL) has newly emerged as a promising paradigm that simulates ICL behaviors in the representation space of large langu

arXiv:2606.02502v1 Announce Type: new Abstract: Multimodal Large Language Models (MLLMs) unify heterogeneous vision-language tasks under a shared generative framework via instruction tuning, yet real-

arXiv:2606.00686v1 Announce Type: new Abstract: The prevailing paradigm in large language model (LLM) alignment operates via erasure, filtering unsafe data or training models to strictly refuse harmfu

arXiv:2510.01800v3 Announce Type: replace Abstract: Academic regulation advising is essential for helping students interpret and comply with institutional policies, yet building effective systems requ

arXiv:2606.01923v1 Announce Type: new Abstract: Large Language Models (LLMs) frequently exhibit 'contextual disregard' when faced with input evidence that conflicts with their internal parametric memo