Beyond Scaling: Agents Are Heading to the Edge
arXiv:2605.18535v1 Announce Type: new Abstract: The bottleneck of useful agentic intelligence has shifted from compressing world knowledge into a single model to executing a coordinated system. This p
Knowledge catalogue
arXiv:2605.18535v1 Announce Type: new Abstract: The bottleneck of useful agentic intelligence has shifted from compressing world knowledge into a single model to executing a coordinated system. This p
arXiv:2604.04932v3 Announce Type: replace Abstract: The misuse of large language models (LLMs) requires precise detection of synthetic text. Existing works mainly follow binary or ternary classificati
arXiv:2605.17652v1 Announce Type: new Abstract: There are not enough established benchmarks for the task fo speech summarization. Creating new benchmarks demands human annotation, as LLMs could embed
arXiv:2605.16908v1 Announce Type: cross Abstract: Security systems demand continuous, cryptograph- ically robust identity verification without requiring subjects to carry physical tokens, smart cards,
arXiv:2605.16728v1 Announce Type: new Abstract: This paper proposes a minimal architecture for body-grounded perspective formation in artificial agents. Extending prior work, the model introduces an i
arXiv:2603.14936v3 Announce Type: replace Abstract: Users often possess a clear visual intent but struggle to articulate it precisely in language. This intention-expression gap makes aligning generate
arXiv:2605.18444v1 Announce Type: cross Abstract: Hardware aging poses a significant challenge for integrated circuits (ICs), leading to performance degradation and eventual failure. In this work, we
arXiv:2605.18180v1 Announce Type: cross Abstract: Wide neural networks in the feature-learning regime drive modern deep learning, and yet they remain far less studied than their kernel-regime counterp
arXiv:2605.17254v1 Announce Type: new Abstract: Property prediction and inverse structural design of catalytic materials are typically modeled as two independent tasks: the former predicts target prop
arXiv:2605.16274v1 Announce Type: cross Abstract: Charts are the dominant medium for visualizing data, discovering patterns and trends, and communicating data driven insights, yet designing them still
arXiv:2605.17214v1 Announce Type: new Abstract: While Large Language Models (LLMs) have revolutionized scientific text processing, they exhibit a significant capability gap when interpreting chemical
arXiv:2605.17458v1 Announce Type: new Abstract: Text classification models are typically trained via supervised fine-tuning (SFT). However, SFT essentially performs behavior cloning from instance-wise
arXiv:2605.18257v1 Announce Type: cross Abstract: Multimodal representation alignment is pivotal for large language models and robotics. Traditional methods are often hindered by cross-modal informati
arXiv:2605.17135v1 Announce Type: new Abstract: Annotating large-scale LiDAR point clouds for 3D semantic segmentation is costly and time-consuming, which motivates the use of semi-supervised learning
arXiv:2503.13934v2 Announce Type: replace-cross Abstract: Mobile robot navigation in dynamic environments with pedestrian traffic is a key challenge in the development of autonomous mobile service rob
arXiv:2605.18045v1 Announce Type: cross Abstract: Robotic systems often use predictive uncertainty to decide whether to act autonomously or defer to a fallback policy. In threshold-gated autonomy, unc
arXiv:2605.16300v1 Announce Type: cross Abstract: Robotic systems are moving from isolated platforms to interconnected multi-agent ecosystems that operate in human environments. This shift raises a go
arXiv:2605.17144v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models leverage powerful perceptual priors from web-scale Vision-Language Model (VLM) pre-training, yet they remain surpr
arXiv:2605.16889v1 Announce Type: new Abstract: Multimodal sentiment analysis relies on textual, acoustic, and visual signals, yet real-world data often suffer from modality missing and quality imbala
arXiv:2605.16704v1 Announce Type: new Abstract: Improving LLM performance on downstream tasks sometimes requires leveraging auxiliary datasets during post-training. In practice, however, developers fa
arXiv:2605.18675v1 Announce Type: cross Abstract: Offline reinforcement learning struggles with distributional shift and constrained performance due to static dataset limitations, while online RL dema
arXiv:2605.18413v1 Announce Type: new Abstract: Automated structural health monitoring is essential to prevent catastrophic infrastructure failures. Precise, pixel-level defect segmentation is needed
arXiv:2605.16806v1 Announce Type: cross Abstract: Collaborative game-based learning environments offer rich opportunities for small-group knowledge construction, yet automatically predicting student c
arXiv:2605.17807v1 Announce Type: cross Abstract: Text-to-Image (T2I) generation has achieved remarkable progress in recent years. Meanwhile, reinforcement learning methods, particularly those based o
arXiv:2605.16342v1 Announce Type: cross Abstract: Diffusion large language models are a compelling alternative to autoregressive models, yet existing RL methods for diffusion treat all denoising steps
arXiv:2605.18608v1 Announce Type: new Abstract: Continual Test-Time Adaptation (CTTA) aims to empower perception systems to handle dynamic distribution shifts encountered after deployment. Existing me
arXiv:2603.08145v2 Announce Type: replace-cross Abstract: Preference-based alignment methods (e.g., RLHF, DPO) typically optimize a single scalar objective, implicitly averaging over heterogeneous hum
arXiv:2605.16989v1 Announce Type: new Abstract: Individualized treatment selection with continuous actions requires accurate causal response estimation in decision-relevant regions, rather than unifor
arXiv:2605.16826v1 Announce Type: cross Abstract: Knowledge distillation is central to LLM post-training, yet its design space remains poorly understood, especially alongside reinforcement learning (R
arXiv:2605.17307v1 Announce Type: cross Abstract: This study develops and evaluates a deep reinforcement learning framework for dynamic portfolio allocation across global equity markets. The Soft Acto
arXiv:2510.26745v3 Announce Type: replace-cross Abstract: Deep sequence models are said to store atomic facts predominantly in the form of associative memory: a brute-force lookup of co-occurring enti
arXiv:2605.17451v1 Announce Type: new Abstract: Aerial object tracking has broad applications in public safety, emergency rescue, wildlife monitoring, and related fields. However, existing aerial trac
arXiv:2605.16937v1 Announce Type: new Abstract: Trajectory-controlled video generation has become essential for controllable video generation. While current methods perform well under small-view camer
arXiv:2605.18722v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models have recently become a central direction in embodied AI, but current systems are restricted to either dual-gripper c
arXiv:2605.17118v1 Announce Type: new Abstract: Differentiable optimization layers are traditionally integrated in predict-then-optimize frameworks where a neural model estimates parameters that subse
arXiv:2508.04149v2 Announce Type: replace-cross Abstract: Aligning large language models (LLMs) with human preferences is a critical challenge in AI research. While methods like Reinforcement Learning
arXiv:2605.16415v1 Announce Type: new Abstract: The creativity of diffusion models refers to their ability to generate highly realistic images that are different from their training data. Creativity i
arXiv:2605.18508v1 Announce Type: cross Abstract: Programmatic reinforcement learning (PRL) offers an interpretable alternative to deep reinforcement learning by representing policies as human-readabl
arXiv:2605.16732v1 Announce Type: new Abstract: Diffusion Transformers (DiTs) achieve state-of-the-art image generation quality but incur substantial memory and computational costs at inference. While
arXiv:2605.17295v1 Announce Type: cross Abstract: Modern reasoning agents are increasingly evaluated on their ability to generate multiple valid solution paths, plans, or tool-use traces for a given i
arXiv:2605.18702v1 Announce Type: cross Abstract: Tabular foundation models (TFMs) achieve strong performance on health datasets, but their inference cost and infrastructure requirements limit practic
arXiv:2605.16776v1 Announce Type: cross Abstract: Mitigating sensitive and harmful outputs is fundamental to ensuring safe deployment of LLMs. Existing approaches typically follow two paradigms: Knowl
arXiv:2605.17694v1 Announce Type: new Abstract: Power differences shape human communication through well documented socio cognitive effects, including language coordination, pronoun usage, authority b
arXiv:2605.17918v1 Announce Type: cross Abstract: Domain transfer (DT) maps source to target distributions and supports tasks such as unsupervised image-to-image translation, single-cell analysis, and
arXiv:2605.16990v1 Announce Type: new Abstract: While 2D diffusion models have achieved remarkable success in identity-preserving personalization, extending this capability to 3D assets remains a sign
arXiv:2603.22056v2 Announce Type: replace Abstract: Large language models (LLMs) achieve state-of-the-art (SOTA) performance across language tasks, but are costly to deploy due to their size and resou
arXiv:2605.17900v1 Announce Type: new Abstract: Accurate Point of Interest (POI) attribute acquisition is essential for location-based services, yet traditional modular Interactive Voice Response (IVR
arXiv:2405.19189v3 Announce Type: replace Abstract: With the great success of diffusion models (DMs) in generating realistic synthetic vision data, many researchers have investigated their potential i
arXiv:2605.17486v1 Announce Type: cross Abstract: Recent progress in Reinforcement Learning (RL) provides a principled approach to optimizing Vision-Language-Action (VLA) models, facilitating a shift
arXiv:2605.17580v1 Announce Type: new Abstract: Electrocardiogram (ECG)-based models have achieved strong performance in diagnostic tasks, yet they remain limited in modeling how cardiac dynamics evol
arXiv:2605.16825v1 Announce Type: cross Abstract: Recently, Generative Recommenders (GRs), characterized by a unified end-to-end framework, have exhibited astonishing potential in transforming the rec
arXiv:2605.16951v1 Announce Type: new Abstract: A fundamental challenge in image editing lies in preserving spatial locality: edits should improve targeted content without inadvertently altering surro
arXiv:2605.17833v1 Announce Type: cross Abstract: Training a deep neural network with noisy labels could reduce data annotation cost but may introduce noise into the learned model. In meta label corre
arXiv:2511.07288v2 Announce Type: replace-cross Abstract: Learning complex policies with Reinforcement Learning (RL) is often hindered by instability and slow convergence, a problem exacerbated by the
arXiv:2605.18233v1 Announce Type: new Abstract: Without incurring significant computational overhead, train-free long video generation aims to enable foundation video generation models to produce long
arXiv:2605.17770v1 Announce Type: new Abstract: The advancement of Large Reasoning Models (LRMs) has catalyzed a paradigm shift from reactive ``fast thinking'' text generation to systematic, step-by-s
arXiv:2605.18078v1 Announce Type: new Abstract: Multi-agent policy-gradient methods have been shown to converge locally near stable Nash equilibria. Local convergence, however, does not determine whic
arXiv:2605.18562v1 Announce Type: cross Abstract: Accurate estimates of item difficulty are essential for valid assessment and effective adaptive learning. However, for newly created tasks, response d
arXiv:2605.16696v1 Announce Type: new Abstract: Face inpainting techniques recover missing or occluded facial regions in a visually realistic manner, but preserving the identity in the final output re
arXiv:2601.21350v2 Announce Type: replace Abstract: A reliable reward model is essential for aligning large language models with human preferences through reinforcement learning from human feedback. H