The Origin of Edge of Stability
arXiv:2604.20446v1 Announce Type: new Abstract: Full-batch gradient descent on neural networks drives the largest Hessian eigenvalue to the threshold 2/eta, where eta is the learning rate. This phenom
Knowledge catalogue
arXiv:2604.20446v1 Announce Type: new Abstract: Full-batch gradient descent on neural networks drives the largest Hessian eigenvalue to the threshold 2/eta, where eta is the learning rate. This phenom
arXiv:2507.21166v2 Announce Type: replace-cross Abstract: Human intelligence scales through cumulative cultural evolution (CCE), a ratchet process in which innovations are retained against entropic dr
arXiv:2603.20714v2 Announce Type: replace Abstract: 3D Gaussian Splatting (3DGS) has become the method of choice for photo-realistic 3D reconstruction of scenes, due to being able to efficiently and a
arXiv:2604.19749v1 Announce Type: new Abstract: Equipping LLMs with external tools effectively addresses internal reasoning limitations. However, it introduces a critical yet under-explored phenomenon
arXiv:2604.19758v1 Announce Type: new Abstract: We present ThermoQA, a benchmark of 293 open-ended engineering thermodynamics problems in three tiers: property lookups (110 Q), component analysis (101
arXiv:2604.01577v2 Announce Type: replace-cross Abstract: We extend the recent latent recurrent modeling to sequential input streams. By interleaving fast, recurrent latent updates with self-organizat
arXiv:2502.11478v3 Announce Type: replace-cross Abstract: In high-noise environments such as factories, subways, and busy streets, capturing clear speech is challenging. Throat microphones can offer a
arXiv:2604.20117v1 Announce Type: new Abstract: Constructivist epistemology argues that knowledge is actively constructed rather than passively copied. Despite the generative nature of Large Language
arXiv:2604.20723v1 Announce Type: cross Abstract: The cost of simulator evaluations is a key practical bottleneck for Simulation Based Inference (SBI). In hierarchical settings with shared global para
arXiv:2604.20614v1 Announce Type: new Abstract: Modern neural networks can achieve high accuracy while remaining poorly calibrated, producing confidence estimates that do not match empirical correctne
arXiv:2604.20123v1 Announce Type: new Abstract: In natural images, object skeletons are used to represent geometric shapes. However, even slight variations in pose or movement can cause noticeable cha
arXiv:2604.20231v1 Announce Type: new Abstract: Connected autonomous vehicles (CAVs), which represent a significant advancement in autonomous driving technology, have the potential to greatly increase
arXiv:2604.20549v1 Announce Type: cross Abstract: As Large Language Models (LLMs) scale, data curation has shifted from maximizing volume to optimizing the signal-to-noise ratio by performing quality
arXiv:2604.20151v1 Announce Type: cross Abstract: Autonomous mechanical thrombectomy (MT) presents substantial challenges due to highly variable vascular geometries and the requirements for accurate,
arXiv:2604.20495v1 Announce Type: cross Abstract: Machine learning-based static malware detectors remain vulnerable to adversarial evasion techniques, such as metamorphic engine mutations. To address
arXiv:2408.00920v4 Announce Type: replace Abstract: In the field of machine unlearning, certified unlearning has been extensively studied in convex machine learning models due to its high efficiency a
arXiv:2604.20374v1 Announce Type: new Abstract: Automated Market Makers (AMMs), as a core infrastructure of decentralized finance (DeFi), uniquely drive on-chain asset pricing through a deterministic
arXiv:2602.10100v2 Announce Type: replace Abstract: Data privacy and eXplainable Artificial Intelligence (XAI) are two important aspects for modern Machine Learning systems. To enhance data privacy, r
arXiv:2604.19778v1 Announce Type: new Abstract: We present KokborokMT, a high-quality neural machine translation (NMT) system for Kokborok (ISO 639-3), a Tibeto-Burman language spoken primarily in Tri
arXiv:2602.12755v2 Announce Type: replace Abstract: Diffusion-based image generators are promising priors for ill-posed inverse problems like sparse-view X-ray Computed Tomography (CT). As most studie
arXiv:2604.20211v1 Announce Type: cross Abstract: Logging code plays an important role in software systems by recording key events and behaviors, which are essential for debugging and monitoring. Howe
arXiv:2604.19934v1 Announce Type: new Abstract: We study how large language models recall relational knowledge during text generation, with a focus on identifying latent representations suitable for r
arXiv:2602.10312v2 Announce Type: replace Abstract: We propose R2RAG-Flood, a training-free retrieval-augmented generation framework for flood damage nowcasting with reinforced reasoning. The framewor
arXiv:2604.20127v1 Announce Type: new Abstract: Failures in complex systems often emerge through gradual degradation and the propagation of stress across interacting components rather than through iso
arXiv:2601.20144v3 Announce Type: replace Abstract: Tool-calling agents are increasingly deployed in real-world customer-facing workflows. Yet most studies on tool-calling agents focus on idealized se
arXiv:2509.22343v2 Announce Type: replace-cross Abstract: Reasoning capability is essential to ensure the factual correctness of the responses of transformer-based Large Language Models (LLMs), and ro
arXiv:2604.19757v1 Announce Type: cross Abstract: This paper presents a transparent screening framework for estimating inference and training impacts of current large language models under limited obs
arXiv:2506.23040v4 Announce Type: replace-cross Abstract: Large language models are thought to have the potential to aid in medical decision making. This work investigates the degree to which this mig
arXiv:2604.20043v1 Announce Type: cross Abstract: Explainability for Large Language Model (LLM) agents is especially challenging in interactive, partially observable settings, where decisions depend o
arXiv:2604.20582v1 Announce Type: cross Abstract: We study emergent social dynamics in LLM agents playing The Resistance: Avalon, a hidden-role deception game. Unlike prior work on single-game perform
arXiv:2604.19769v1 Announce Type: cross Abstract: Key-value (KV) caching is critical for efficient inference in large language models (LLMs), yet its memory footprint scales linearly with context leng
arXiv:2604.17172v2 Announce Type: replace-cross Abstract: The rapid growth of large language models (LLMs) has made GPU communication a critical bottleneck. While prior work reduces communication volu
arXiv:2604.20255v1 Announce Type: cross Abstract: Anomaly detection in tabular data is challenging due to high dimensionality, complex feature dependencies, and heterogeneous noise. Many existing meth
arXiv:2603.16059v2 Announce Type: replace Abstract: Motion planning under dynamics constraints, i.e, kinodynamic planning, enables safe robot operation by generating dynamically feasible trajectories
arXiv:2512.12463v3 Announce Type: replace-cross Abstract: Classical statistical learning theory predicts a U-shaped relationship between test loss and model capacity, driven by the bias-variance trade
arXiv:2511.19328v2 Announce Type: replace Abstract: Language modeling has shown us that transformers can discover latent structure from context, but the dynamics of how they acquire different componen
arXiv:2604.19923v1 Announce Type: new Abstract: We introduce UniCon3R (Unified Contact-aware 3D Reconstruction), a unified feed-forward framework for online human-scene 4D reconstruction from monocula
arXiv:2604.20318v1 Announce Type: new Abstract: Composed image retrieval, multi-turn composed image retrieval, and composed video retrieval all share a common paradigm: composing the reference visual
arXiv:2604.20421v1 Announce Type: new Abstract: Prediction markets are markets for trading claims on future events, such as presidential elections, and their prices provide continuously updated signal
arXiv:2510.11041v2 Announce Type: replace Abstract: In future intelligent transportation systems, autonomous cooperative planning (ACP), becomes a promising technique to increase the effectiveness and
arXiv:2604.19788v1 Announce Type: new Abstract: As Artificial Intelligence (AI) systems continue to grow in size and complexity, so does the difficulty of the quest for AI transparency. In a world of
arXiv:2604.19801v1 Announce Type: cross Abstract: Automatic Speech Recognition (ASR) is increasingly used in applications involving child speech, such as language learning and literacy acquisition. Ho
arXiv:2308.00513v2 Announce Type: replace Abstract: This paper introduces UVIO, a multi-sensor framework that leverages Ultra Wide Band (UWB) technology and Visual-Inertial Odometry (VIO) to provide r
arXiv:2604.20755v1 Announce Type: new Abstract: We introduce V-tableR1, a process-supervised reinforcement learning framework that elicits rigorous, verifiable reasoning from multimodal large language
arXiv:2603.26842v2 Announce Type: replace-cross Abstract: Time series anomaly detection (TSAD) is essential for maintaining the reliability and security of IoT-enabled service systems. Existing method
arXiv:2604.20682v1 Announce Type: new Abstract: We present a systematic empirical study of transformer compression through over 40 experiments on GPT-2 (124M parameters) and Mistral 7B (7.24B paramete
arXiv:2408.00929v2 Announce Type: replace Abstract: As privacy concerns escalate in the realm of machine learning, data owners now have the option to utilize machine unlearning to remove their data fr
arXiv:2602.22437v3 Announce Type: replace-cross Abstract: Fully Sharded Data Parallel (FSDP), also known as Zero Redundancy Optimizer (ZeRO), is widely used for large-scale model training, because of
arXiv:2604.20210v1 Announce Type: cross Abstract: Individual differences in vibrotactile perception underscore the growing importance of personalization as haptic feedback becomes more prevalent in in
arXiv:2604.20473v1 Announce Type: new Abstract: Existing Video Large Language Models (Video LLMs) struggle with complex video understanding, exhibiting limited reasoning capabilities and potential hal
arXiv:2604.19945v1 Announce Type: new Abstract: In this paper, we investigate the problem of how to effectively master tool-use to solve complex visual reasoning tasks for Multimodal Large Language Mo
arXiv:2604.20712v1 Announce Type: new Abstract: Peg-in-hole (PiH) assembly is a fundamental yet challenging robotic manipulation task. While reinforcement learning (RL) has shown promise in tackling s
arXiv:2604.20444v1 Announce Type: cross Abstract: Embodied intelligence has advanced rapidly in recent years; however, bimanual manipulation-especially in contact-rich tasks remains challenging. This
arXiv:2604.19858v1 Announce Type: new Abstract: We present Wan-Image, a unified visual generation system explicitly engineered to paradigm-shift image generation models from casual synthesizers into p
arXiv:2604.20398v1 Announce Type: new Abstract: While Large Language Models (LLMs) excel at function-level code generation, project-level tasks such as generating functional and visually aesthetic mul
arXiv:2604.20213v1 Announce Type: new Abstract: Accurate segmentation of maxillary sinus in panoramic X-ray images is essential for dental diagnosis and surgical planning; however, this task remains r
arXiv:2601.17609v2 Announce Type: replace Abstract: In domains like medicine and finance, large-scale labeled data is costly and often unavailable, leading to models trained on small datasets that str
arXiv:2604.19850v1 Announce Type: cross Abstract: Biological systems are promising substrates for computation because they naturally process environmental information through complex internal dynamics
arXiv:2604.19998v1 Announce Type: new Abstract: Evaluating AI-generated reviews by verdict agreement is widely recognized as insufficient, yet current alternatives rarely audit which concerns a system
arXiv:2604.20749v1 Announce Type: new Abstract: Situated conversational recommendation (SCR), which utilizes visual scenes grounded in specific environments and natural language dialogue to deliver co