Knowledge catalogue
arXiv:2606.26050v1 Announce Type: cross Abstract: Midway through an ordinary pretraining run, a small language model learns the pronoun-gender rule: cued with a girl's name ('Sue cried because'), it r
arXiv:2606.25844v1 Announce Type: new Abstract: A common practice converts a one-dimensional signal into an image so that a vision backbone pretrained on natural photographs can be reused for recognit
arXiv:2606.26080v1 Announce Type: new Abstract: Process reward models enable fine-grained, step-level evaluation of LLMs, yet building them for agentic settings remains prohibitively difficult: long-h
arXiv:2606.25365v1 Announce Type: new Abstract: We present a study on low-resource machine translation for the Tangkhul-English (nmf-en) language pair. Tangkhul is a severely under-resourced Tibeto-Bu
arXiv:2606.25087v1 Announce Type: new Abstract: Neural network quantization aims to find a discrete representation of parameters that preserves the performance of a full-precision (FP) model as faithf
arXiv:2606.25185v1 Announce Type: new Abstract: Accurately predicting the spatiotemporal evolution of amyloid-eta and tau proteins at the individual level is critical for improving the diagnosis and t
arXiv:2606.25008v1 Announce Type: cross Abstract: Neural scaling laws describe how pre-training loss decays as power laws with training time, model size, and compute. This position paper argues that t
arXiv:2606.25009v1 Announce Type: new Abstract: Ultrasound is a non-invasive, real-time, and cost-effective imaging technique widely used in clinical diagnosis. However, its diagnostic efficacy is oft
arXiv:2606.25389v1 Announce Type: new Abstract: Extracting skills from multi-agent offline dataset improves learning efficiency via sharing task-invariant coordination skills among tasks. In settings
arXiv:2504.17247v3 Announce Type: replace Abstract: Deep learning-based antimicrobial peptide (AMP) discovery faces critical challenges such as limited controllability, lack of representations that ef
arXiv:2606.25325v1 Announce Type: new Abstract: We find that current emotion-oriented Omni-MLLMs still lack reliable omni-modal perception: they (i) underutilize multimodal cues in their reasoning tra
arXiv:2606.24900v1 Announce Type: new Abstract: This paper proposes a new approach to near-sensor computing, in which a lightweight Neural Architecture Search (NAS) is performed directly on the deploy
arXiv:2606.26091v1 Announce Type: new Abstract: On-policy self-distillation achieves strong pass@1 accuracy by using a single model as both teacher and student, with the teacher conditioned on a corre
arXiv:2606.25762v1 Announce Type: new Abstract: In oncology, access to patient-level data is often restricted. Synthetic data provides an alternative for analyzing treatment effectiveness, but existin
arXiv:2606.25575v1 Announce Type: new Abstract: Assistive robotic systems face a fundamental trade-off: fully autonomous systems lack user agency, while fully user-controlled systems demand continuous
arXiv:2606.25757v1 Announce Type: new Abstract: Reinforcement Learning (RL) has enabled LLMs to excel in objective reasoning tasks such as mathematics and code generation. However, applying RL to open
arXiv:2606.17460v2 Announce Type: replace Abstract: Neural operators are widely used as surrogate solution maps for partial differential equations (PDEs), but full-size models can be costly to store,
arXiv:2606.25462v1 Announce Type: new Abstract: Abstractive text summarization is the technique of generating a short and concise summary comprising the salient ideas of a source text without making a
arXiv:2606.25906v1 Announce Type: new Abstract: With the advancement of artificial intelligence, research on oracle bone scripts has entered a new era. However, existing methods and benchmarks remain
arXiv:2606.25245v1 Announce Type: new Abstract: Continuous 6-DoF pose estimation is essential for autonomous UAV operations. Yet, existing visual odometry and SLAM methods accumulate drift and yield o
arXiv:2606.25935v1 Announce Type: new Abstract: Was this person ever at that place, and if so, when? Answering such questions from noisy, multilingual historical documents is the central challenge of
arXiv:2601.13317v2 Announce Type: replace Abstract: Climate discourse online shapes public understanding of climate change and informs political and policy debate, yet it unfolds across structurally d
arXiv:2606.25534v1 Announce Type: new Abstract: Implicit Neural Representation (INR) provides an effective approach for continuous signal modeling, but classical per-pixel inference results in quadrat
arXiv:2606.24952v1 Announce Type: new Abstract: A central aspiration of mechanistic interpretability is controllability: if we know where a behavior is represented in a model's activations, we should
arXiv:2507.20068v3 Announce Type: replace Abstract: Off-policy evaluation (OPE) methods estimate the value of a new reinforcement learning (RL) policy prior to deployment. Recent advances have shown t
arXiv:2507.01695v3 Announce Type: replace Abstract: Deep neural networks (DNNs) are widely used for their ability to model complex patterns across domains such as computer vision, speech recognition,
arXiv:2606.18008v2 Announce Type: replace Abstract: Visual attribution is a fundamental tool for interpreting modern vision and vision-language models, particularly when their decisions must be inspec
arXiv:2606.23049v2 Announce Type: replace Abstract: Phones are becoming an important execution surface for general-purpose agents, but training open models for reliable phone use remains difficult bec
arXiv:2606.25181v1 Announce Type: cross Abstract: Early identification of speech sound errors in children is often limited by access to specialists, motivating lightweight screening tools that can ope
arXiv:2603.19305v2 Announce Type: replace-cross Abstract: Humanoid robots are expected to execute agile and expressive whole-body motions in real-world settings. Existing text-to-motion generation mod
arXiv:2606.15053v2 Announce Type: replace Abstract: Surrogate models are central to scientific machine learning, where they enable fast prediction, simulation, inference, and control for complex physi
arXiv:2606.25306v1 Announce Type: new Abstract: Video generation models are increasingly capable of producing realistic videos, but they still struggle to generate videos that follow basic physical la
arXiv:2604.25345v2 Announce Type: replace Abstract: Agentic AI systems are increasingly being integrated into scientific workflows, yet their behavior under realistic conditions remains insufficiently
arXiv:2606.25740v1 Announce Type: new Abstract: 3D anomaly detection in point clouds is critical for high-precision industrial manufacturing. Reconstruction-based methods have laid a strong foundation
arXiv:2606.25442v1 Announce Type: new Abstract: Safety alignment of large language models (LLMs) typically depends on high-quality supervision data, such as safe demonstrations or preference pairs. Ho
arXiv:2507.16863v2 Announce Type: replace-cross Abstract: A common belief in multimodal research is that the perceptual weaknesses of vision--language models can be compensated by stronger language re
arXiv:2606.25719v1 Announce Type: new Abstract: In this paper, we introduce position graphs, a graph-based reasoning framework based on the formalization of position spaces. This framework utilizes tw
arXiv:2606.25680v1 Announce Type: new Abstract: Underwater vehicles operate from a fixed onboard energy budget that propulsion rapidly depletes, so a controller that completes its task while drawing l
arXiv:2606.25098v1 Announce Type: cross Abstract: The rapid expansion of artificial intelligence (AI) infrastructure is driving unprecedented growth in electricity demand from data centers. Traditiona
arXiv:2606.25256v1 Announce Type: new Abstract: We introduce Pre-Warm, a simple yet effective zero-training-cost method for data-conditioned initialization of the first convolutional layer. Before the
arXiv:2606.25430v1 Announce Type: new Abstract: Reconstructing 3D scenes from a single image is a fundamental challenge in computer vision, with broad applications in virtual reality, robotics, and co
arXiv:2405.17423v4 Announce Type: replace-cross Abstract: As Visual Language Models (VLMs) become increasingly embedded in everyday applications, ensuring they can recognise and appropriately handle p
arXiv:2606.24938v1 Announce Type: cross Abstract: Tensor decomposition of donor imes cell-type imes gene single-cell data recovers multicellular programs: coordinated axes of inter-individual transcri
arXiv:2606.26021v1 Announce Type: cross Abstract: Tabular foundation models are commonly assumed to present limited privacy concerns as they are often pre-trained on large collections of synthetic dat
arXiv:2606.25149v1 Announce Type: cross Abstract: The last few years have seen a significant rise in interest in highly autonomous and proactive systems, fueled by advances in AI. Systems that anticip
arXiv:2606.25622v1 Announce Type: cross Abstract: The NIS-2 Directive mandates robust Risk Management from thousands of small and medium enterprises. To ensure compliance, companies rely on establishe
arXiv:2606.25459v1 Announce Type: new Abstract: While self-supervised speech models have achieved strong performance across speech tasks, relatively little is known about how their internal phonetic r
arXiv:2606.24965v1 Announce Type: cross Abstract: Reasoning about relational structures remains a significant challenge for neural models, particularly when they must systematically apply learned know
arXiv:2606.25956v1 Announce Type: new Abstract: Risk stratification for pulmonary embolism (PE) is critical for clinical decision-making. Stratification guidelines are based on patient medical records
arXiv:2405.01741v4 Announce Type: replace-cross Abstract: Reliability of AI systems is a fundamental concern for the successful deployment and widespread adoption of AI technologies. Unfortunately, th
arXiv:2606.24974v1 Announce Type: new Abstract: Explainability techniques are used to assess the output of various deep learning models. This is especially true in healthcare, where models need to be
arXiv:2606.25519v1 Announce Type: cross Abstract: Quantization is widely used to reduce the inference cost of large language models, but its effect on reasoning models is not fully captured by final-a
arXiv:2603.01470v3 Announce Type: replace Abstract: We consider the optimization problem of an expensive-to-evaluate black-box function, in which we can obtain noisy function values in parallel. For t
arXiv:2606.25750v1 Announce Type: cross Abstract: Safety evaluation of large language models (LLMs) is commonly performed by querying models with unsafe or jailbreak prompts and judging whether their
arXiv:2606.25480v1 Announce Type: cross Abstract: Unmanned aerial vehicle (UAV) can provide on-demand, high-capacity connectivity in disaster and normal situation. However, it faces a challenge of cur
arXiv:2602.12390v2 Announce Type: replace Abstract: We study neural networks with trainable low-degree rational activation functions and show that they are more expressive and parameter-efficient than
arXiv:2606.25206v1 Announce Type: cross Abstract: Long-term robot deployment requires a compact and scalable memory that preserves fine-grained visual semantics, grounds observations in space and time
arXiv:2606.25770v1 Announce Type: cross Abstract: Data scarcity is a major bottleneck in medical Multiple Instance Learning (MIL), especially for rare diseases or expensive modalities. We introduce a
arXiv:2602.11575v3 Announce Type: replace-cross Abstract: Visual navigation models often struggle in real-world dynamic environments due to limited robustness to the sim-to-real gap and the difficulty
arXiv:2606.26083v1 Announce Type: new Abstract: Speech conveys information through both words and vocal delivery. We evaluate four leading production realtime voice systems-OpenAI's GPT Realtime 2, Go