Self-Improving In-Context Learning
arXiv:2605.23180v1 Announce Type: new Abstract: We propose to improve in-context learning (ICL) by optimizing the continuous embeddings of a fixed few-shot prompt at test time. The key observation is
Knowledge catalogue
arXiv:2605.23180v1 Announce Type: new Abstract: We propose to improve in-context learning (ICL) by optimizing the continuous embeddings of a fixed few-shot prompt at test time. The key observation is
arXiv:2605.23239v1 Announce Type: new Abstract: Defending Graph Neural Networks (GNNs) against adversarial attacks requires balancing accuracy and robustness, a trade-off often mishandled by tradition
arXiv:2605.23160v1 Announce Type: cross Abstract: We present Semantic-Aware Guided Exploration, SAGE, a system for open-vocabulary exploration in unknown 3D indoor environments that preserves coverage
arXiv:2605.23477v1 Announce Type: new Abstract: Diffusion-based policies have established a new standard for precise robotic manipulation but face a critical scalability bottleneck: high-performance m
arXiv:2603.14027v2 Announce Type: replace Abstract: Political speakers often avoid answering questions directly while maintaining the appearance of responsiveness. Despite its importance for public di
arXiv:2605.23832v1 Announce Type: new Abstract: Deploying heterogeneous multi-agent robot fleets for collaborative perception requires robust data exchange and scalable software architectures. However
arXiv:2605.23240v1 Announce Type: new Abstract: This paper investigates continuous-time motion planning under Signal Temporal Logic (STL) specifications. The goal is to generate smooth robot trajector
arXiv:2605.23245v1 Announce Type: cross Abstract: Video object insertion requires ensuring spatio-temporal coherence and interactive realism, extending far beyond simple content placement. However, cu
arXiv:2605.23904v1 Announce Type: new Abstract: Agent skills today are hand-crafted, generated one-shot, or evolved through loosely controlled self-revision, none of which behaves like a deep-learning
arXiv:2605.23144v1 Announce Type: new Abstract: Existing language-image pre-training for remote sensing object detection is constrained by Monolithic Label Learning, which relies on exhaustively enume
arXiv:2605.23891v1 Announce Type: new Abstract: Mask-free video object insertion has emerged as a challenging task, requiring harmonious integration of reference objects into source videos. However, e
arXiv:2605.23017v1 Announce Type: new Abstract: One prominent method of evaluating machine learning model trustworthiness is the notion of calibration. In the binary outcome setting, a probabilistic p
arXiv:2605.23426v1 Announce Type: cross Abstract: Socially fluent agentic AI can now participate in online interaction in ways that resemble ordinary human conversation, potentially weakening people's
arXiv:2605.23592v1 Announce Type: new Abstract: Dismantling aircrafts reaching their end of life is a complex endeavour that is necessary in terms of sustainability but yields small income margins for
arXiv:2605.23898v1 Announce Type: new Abstract: Vision-Language Models (VLMs) are increasingly deployed in embodied environments, where they need produce numerical outputs such as action magnitudes an
arXiv:2605.23035v1 Announce Type: cross Abstract: Intermediate layers of large language models (LLMs) best predict human brain responses to language, one of the most robust findings in computational n
arXiv:2605.23341v1 Announce Type: cross Abstract: Embodied trajectories, such as the executable motion sequences of robotic manipulators, underwater vehicles, and mobile robots, are a fundamental outp
arXiv:2605.23424v1 Announce Type: cross Abstract: In-network learning (INL) trains distributed neural modules by exchanging latent activations and backpropagated errors over a communication graph. Thi
arXiv:2510.21270v2 Announce Type: replace-cross Abstract: Scaling the context length of large language models (LLMs) offers significant benefits but is computationally expensive. This expense stems pr
arXiv:2603.10453v2 Announce Type: replace Abstract: This study proposes a multi-resolution Convolutional Long Short-Term Memory (ConvLSTM) ensemble framework that leverages diverse temporal input reso
arXiv:2605.23288v1 Announce Type: new Abstract: Recent Open-Vocabulary Action Recognition (OVAR) methods typically aggregate visual features into a global representation before computing text alignmen
arXiv:2412.14642v4 Announce Type: replace Abstract: Recently, Large Language Models (LLMs) have demonstrated great potential in natural language-driven molecule discovery. However, existing datasets a
arXiv:2505.21573v3 Announce Type: replace-cross Abstract: Learning PDE dynamics from limited data with unknown physics is challenging. Existing neural PDE solvers either require large datasets or rely
arXiv:2605.23306v1 Announce Type: cross Abstract: Active traffic management (ATM) is frequently hindered by traditional macroscopic models and rigid empirical thresholds that fail to capture metastabl
arXiv:2605.23440v1 Announce Type: cross Abstract: Joint Entity and Relation Extraction (JERE) is highly susceptible to weak generalization due to low-quality training data. Data augmentation is a comm
arXiv:2605.22859v1 Announce Type: cross Abstract: Automated sleep staging is commonly approached as a supervised machine learning problem, with deep learning methods dominating recent research. While
arXiv:2605.23137v1 Announce Type: cross Abstract: Electroencephalography (EEG) visual decoding remains challenging due to the modality gap between low-SNR neural signals and highly structured vision--
arXiv:2605.23040v1 Announce Type: new Abstract: Latent steering exploits internal representations of Large Language Models (LLMs) to guide generation, yet interventions on dense states can entangle di
arXiv:2605.23237v1 Announce Type: new Abstract: Stereo image and video generation, stereo geometry estimation, and condition-controlled view synthesis require paired data in which the variables that d
arXiv:2605.22841v1 Announce Type: cross Abstract: What happens when the strongest alliance member pressures a weaker member over territory and strategic control? We examine the Greenland sovereignty c
arXiv:2605.23857v1 Announce Type: cross Abstract: Knowledge distillation generally assumes a strong-to-weak relationship where stronger teachers yield better students. In this work, we examine this as
arXiv:2605.23597v1 Announce Type: new Abstract: Matching person names across heterogeneous records is a core challenge in entity resolution, especially within linguistically and culturally complex env
arXiv:2605.22904v1 Announce Type: cross Abstract: Understanding and monitoring human behavior in metro stations play an important role in supporting suicide prevention efforts, where early identificat
arXiv:2509.15105v3 Announce Type: replace Abstract: Time series forecasting (TSF) is critical in domains like energy, finance, healthcare, and logistics, requiring models that generalize across divers
arXiv:2412.19098v4 Announce Type: replace Abstract: Model merging combines independently trained models into a single multi-task model. However, most existing approaches focus primarily on avoiding ta
arXiv:2604.00003v2 Announce Type: replace-cross Abstract: Extracting structured information from academic PDF documents is non trivial: a single page typically combines free text metadata with tabular
arXiv:2602.01665v2 Announce Type: replace-cross Abstract: The design of environments plays a critical role in shaping the development and evaluation of cooperative multi-agent reinforcement learning (
arXiv:2605.23568v1 Announce Type: new Abstract: Manipulating fragile deformable containers, such as disposable plastic cups filled with liquid, demands real-time grip-force adaptation within an extrem
arXiv:2502.07295v2 Announce Type: replace Abstract: Neural Networks (NNs) for causal effect estimation have shown strong empirical performance, yet endowing them with desirable semiparametric properti
arXiv:2601.21500v2 Announce Type: replace Abstract: In many applications of LLMs, natural language responses often have an underlying structure such as representing discrete labels, numerical values,
arXiv:2601.21692v2 Announce Type: replace Abstract: Fine-Tuning-as-a-Service (FTaaS) facilitates the customization of Multimodal Large Language Models (MLLMs) but introduces critical backdoor risks vi
arXiv:2602.08404v2 Announce Type: replace Abstract: Diffusion large language models (dLLMs) have recently gained significant attention due to their inherent support for parallel decoding. Building on
arXiv:2605.22884v1 Announce Type: cross Abstract: Autoregressive Transformer KV caches grow linearly with context length; sliding-window caching bounds memory but discards evicted tokens entirely, so
arXiv:2605.22984v1 Announce Type: cross Abstract: Test-Time Training (TTT) is an emerging paradigm that enables models to adapt their parameters during inference, improving performance on tasks such a
arXiv:2605.23080v1 Announce Type: new Abstract: Feature attribution methods promise to identify which input features matter for a model output. In generative language models, however, it is often uncl
arXiv:2605.22840v1 Announce Type: cross Abstract: How much thinking can a civilisation do? Kardashev's (1964) typology ranks civilisations by total power: planetary (Type I, ~10^16 W), stellar (Type I
arXiv:2605.23024v1 Announce Type: new Abstract: Large language models now write software, draft legal documents, and produce clinical notes, yet fundamental limits, from Turing and Arrow to the No Fre
arXiv:2605.23071v1 Announce Type: new Abstract: Large language models (LLMs) increasingly rely on long-context processing, but expanding context windows introduces substantial computational and financ
arXiv:2605.23087v1 Announce Type: new Abstract: Neural collapse (NC) describes the structured geometry that emerges in the features and weights of trained classifiers. Recent theory suggests NC can be
arXiv:2605.22842v1 Announce Type: cross Abstract: Multi-agent AI pipelines typically assume that agent misconduct originates from model misalignment. We identify a structural failure in this assumptio
arXiv:2605.23778v1 Announce Type: cross Abstract: Could it be that AI weather models are solving physical equations, although they may not be the equations used by conventional NWP models? We compute
arXiv:2605.22870v1 Announce Type: cross Abstract: Chain-of-thought (CoT) prompting is necessary for arithmetic in small language models, yet shuffling its steps preserves most performance. What does C
arXiv:2601.21306v2 Announce Type: replace-cross Abstract: This paper investigates search in model-based reinforcement learning (RL). Conventional wisdom holds that long-term predictions and compoundin
arXiv:2605.23045v1 Announce Type: cross Abstract: Video representation learning has seen tremendous progress in recent years. This has been driven by many factors, including the scale of training and
arXiv:2605.23081v1 Announce Type: new Abstract: Efficient attention algorithms are critical to mitigate the quadratic cost of attention in long-context workloads. Prior work utilises block-scaled quan
arXiv:2506.04390v2 Announce Type: replace-cross Abstract: Retrieval-augmented generation (RAG) systems are vulnerable to attacks that inject poisoned passages into the retrieved context, even at low c
arXiv:2605.22853v1 Announce Type: cross Abstract: Many modern datasets are large and carry complex structural relationships. Graph-based methods have traditionally been used to represent networked dat
arXiv:2605.23872v1 Announce Type: new Abstract: We introduce training-free looped transformers, in which a lightweight inference-time wrapper loops a contiguous mid-stack block of layers of a frozen c
arXiv:2603.04005v2 Announce Type: replace-cross Abstract: The rate-distortion-perception (RDP) tradeoff characterizes the fundamental limits of lossy compression by jointly considering bitrate, recons
arXiv:2605.22902v1 Announce Type: cross Abstract: Generative Vision-Language Models (VLMs) perform well on multimodal reasoning, but how visual inputs are transformed to text remains poorly understood