Search: “routing”

You don't need heavyweight VLMs to OCR simple text-only PDFs. Doing that is like bringing a bazooka to a knife-fight, and is completely unnecessary and worse quality than a tuned OCR approach. Output

If you’re an IT leader, you might be getting a lot of questions about how to build and deploy agents. The pressure to move fast is intense, but the engineering reality is incredibly complex. Where do

arXiv:2607.04758v1 Announce Type: new Abstract: Physical design quality-of-results~(QoR) optimization is hard and expensive. Choices made at one stage can help or hurt later stages. Each evaluation re

arXiv:2607.02592v1 Announce Type: new Abstract: On-policy distillation (OPD) has recently emerged as an effective post-training paradigm by providing supervision on student-generated trajectories. How

arXiv:2607.05238v1 Announce Type: new Abstract: JEPA world models predict the next latent state with a single deterministic predictor trained by latent regression. We show that this fails structurally

arXiv:2607.04089v1 Announce Type: new Abstract: Lifelong agents need more than larger context windows and better retrieval. They need memories that can persist, evolve, and be corrected without forcin

arXiv:2607.04576v1 Announce Type: new Abstract: LLM agents increasingly answer questions against knowledge bases they help maintain. A common intuition holds that progressive disclosure, a compact cat

arXiv:2607.03598v1 Announce Type: cross Abstract: When a person shares something with a language model, the model often answers the surface of the message rather than what the sender was doing by send

arXiv:2607.04951v1 Announce Type: cross Abstract: Standard distributed ac{llm} schedulers rely on static token counts or rolling latency averages, making them susceptible to failures on statutorily co

spending the last week at @aidotengineer was awesome. too many great convos to cover them all, but jotted down some things that stood out: - Lots of discussion around open source models. I spoke with

arXiv:2607.01789v1 Announce Type: cross Abstract: Mixture-of-Experts (MoE) models scale efficiently but remain costly to adapt due to redundant experts and uniform parameter allocation. Existing param

arXiv:2607.02381v1 Announce Type: new Abstract: This paper describes the participation of HULAT2-UC3M in the Spanish track of MER-TRANS 2026, a shared task on multilingual Easy-to-Read translation. Th

arXiv:2607.01631v1 Announce Type: new Abstract: There nowadays is a myriad of approaches to real-time avoidance of fixed obstacles for unmanned surface vehicles (USVs) and, to a lesser extent, also th

arXiv:2607.01674v1 Announce Type: new Abstract: In multi-source ECG deployment, models may need to incorporate new data sources when earlier raw ECGs cannot be retained or replayed. Freezing a pretrai

arXiv:2607.01992v1 Announce Type: new Abstract: Large-scale battery energy storage systems (BESSs) require O&M decisions that combine alarms, cell-level measurements, device topology, diagnostic table

arXiv:2607.00041v1 Announce Type: cross Abstract: Multi-agent LLM systems can decompose software-engineering work into planning, generation, validation, and repair, but a narrower systems problem rema

arXiv:2607.00457v1 Announce Type: new Abstract: Embodied agents operating in the real world require multi-scale reasoning and knowledge adaptation as conditions change. We identify two challenges in a

arXiv:2607.01021v1 Announce Type: new Abstract: Large-scale crowd management requires pedestrian simulations that are both computationally efficient and compatible with feedback-based control. However

arXiv:2607.00606v1 Announce Type: new Abstract: Recent work on Thinking with Images makes vision a dynamic part of reasoning, but does so through generation: the model invokes external tools, synthesi

arXiv:2606.31700v1 Announce Type: new Abstract: Biological neural circuits obey Dale's principle: each neuron's synapses are uniformly excitatory or inhibitory. Artificial networks that respect this c

arXiv:2606.31331v1 Announce Type: new Abstract: Collaborative inference can improve predictive performance by integrating complementary information across agents, but applying collaborative fusion to

Editor’s note: SOCRadar is a leading cybersecurity company that provides threat intelligence to businesses worldwide. As the volume of cyber threats continued to grow, SOCRadar needed to modernize its

arXiv:2606.28367v1 Announce Type: cross Abstract: Retrieval-augmented generation (RAG) is routinely extended with methods meant to improve retrieval: query expansion, hierarchical and cross-document s

arXiv:2606.28876v1 Announce Type: new Abstract: Long-context language models often conflate two different goals: compressing history into an efficient state, and maintaining reliable long-term memory.

arXiv:2606.29425v1 Announce Type: new Abstract: Existing multi-agent debate frameworks suffer from two critical limitations: they rely on static architectures where agent roles and coordination patter

arXiv:2606.29403v1 Announce Type: cross Abstract: Conformal prediction guarantees marginal coverage, but pooled calibration averages over heterogeneous regions and can mask regional undercoverage in s

arXiv:2606.29532v1 Announce Type: cross Abstract: Integrating unstructured data into relational database systems is increasingly important as demand grows for natural language querying and analysis. A

arXiv:2606.29484v1 Announce Type: cross Abstract: Modern deepfake detectors are rarely consumed as bare classifiers. In moderation, provenance, and verification pipelines their output probability is r

arXiv:2601.07965v2 Announce Type: replace Abstract: When a model knows when it does not know, many possibilities emerge. The first question is how to enable a model to recognize that it does not know.

Welcome to the second Cloud CISO Perspectives for June 2026. Today, we’re discussing how we use AI to chart a path to autonomous software development lifecycle security.As with all Cloud CISO Perspect

arXiv:2606.26603v1 Announce Type: new Abstract: Handheld data collection systems, such as the Universal Manipulation Interface (UMI), enable scalable data collection across diverse environments but on

arXiv:2606.27377v1 Announce Type: cross Abstract: Modern image generation demands a single model that unifies diverse capabilities, including text-to-image (T2I), local editing, and global editing. Ho

arXiv:2606.26017v1 Announce Type: new Abstract: In autonomous driving, diffusion-based planners have emerged as a promising paradigm for robust motion planning in dense and interactive traffic, as the

arXiv:2606.21428v2 Announce Type: replace-cross Abstract: Mixture-of-Experts (MoE) language models are often described as ideal for resource-constrained inference. Each token activates only a small su

arXiv:2606.24062v1 Announce Type: cross Abstract: Financial time series forecasting presents structural challenges absent from standard benchmarks. Log-returns are non-stationary, exhibit exceptionall

arXiv:2606.24448v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models require large-scale video-action pairs, yet real teleoperation remains scarce. While generated robot videos offer a

arXiv:2606.24598v1 Announce Type: cross Abstract: While expert-validated 'LLM + script' workflows deliver significant value, they remain static: they encode hard-won domain knowledge yet fail to adapt

arXiv:2606.24119v1 Announce Type: cross Abstract: Discrete diffusion language model (DLM) fine-tuning inherits inexpensive diagnostics from denoising-time confidence monitors, but their PEFT-training

arXiv:2606.23609v1 Announce Type: cross Abstract: Machine learning models exploit spurious correlations, achieving high average accuracy but failing disproportionately on underrepresented subgroups. E

arXiv:2606.19025v2 Announce Type: replace Abstract: Pre-training Large Language Models (LLMs) typically demands large-scale infrastructure with tightly coupled hardware accelerators. Mixture-of-Expert

arXiv:2606.20961v1 Announce Type: new Abstract: Continual adaptation is essential for multimodal large language models (MLLMs) deployed across evolving domains, but the state-of-the-art MR-LoRA method

arXiv:2606.21033v1 Announce Type: cross Abstract: Image compression for machines calls for a unified codec that serves multiple downstream vision tasks. Existing approaches either adopt task-specific

arXiv:2606.23543v1 Announce Type: cross Abstract: Scaling reinforcement learning for visual mathematical reasoning requires more than generating harder questions: as data volume grows, the reward labe

arXiv:2603.08501v3 Announce Type: replace Abstract: Large language models (LLMs) can answer religious knowledge queries fluently, yet they often hallucinate and misattribute sources, which is especial

arXiv:2606.11712v1 Announce Type: cross Abstract: User-side memory in LLMs is typically scored as a single 'personalization' capability: given a user's history, is the output more user-aware? We show

arXiv:2606.12306v1 Announce Type: new Abstract: Safe ground navigation in large, threat-augmented environments requires aerial support that actively reduces the risks that a ground vehicle faces along