Dual Ascent Diffusion for Inverse Problems
arXiv:2505.17353v2 Announce Type: replace-cross Abstract: Ill-posed inverse problems are fundamental in many domains, ranging from astrophysics to medical imaging. Emerging diffusion models provide a
Knowledge catalogue
arXiv:2505.17353v2 Announce Type: replace-cross Abstract: Ill-posed inverse problems are fundamental in many domains, ranging from astrophysics to medical imaging. Emerging diffusion models provide a
arXiv:2605.15100v1 Announce Type: new Abstract: Large Language Models (LLMs) have demonstrated remarkable abilities in reasoning. However, maximizing their potential through inference-time scaling fac
arXiv:2605.14057v1 Announce Type: new Abstract: Most existing dialogue systems are user-driven, primarily designed to fulfill user requests. However, in many critical real-world scenarios, a conversat
arXiv:2605.14391v1 Announce Type: new Abstract: Learned image compression (LIC) increasingly requires reconstructions that balance distortion fidelity and perceptual realism across a wide range of bit
arXiv:2605.14104v1 Announce Type: new Abstract: Inferring spatially resolved gene expression from histology images offers a cost-effective complement to spatial transcriptomics (ST). However, existing
arXiv:2502.00270v3 Announce Type: replace-cross Abstract: The performance of an LLM depends heavily on the relevance of its training data to the downstream evaluation task. However, in practice, the d
arXiv:2605.14420v1 Announce Type: new Abstract: Current Large Language Models (LLMs) typically rely on coarse-grained national labels for pluralistic value alignment. However, such macro-level supervi
arXiv:2605.14323v1 Announce Type: cross Abstract: We investigate the temporal concatenation of sub-policies in Markov Decision Processes (MDP) with time-varying reward functions. We introduce General
arXiv:2602.02711v2 Announce Type: replace Abstract: Large language models (LLMs) achieve strong performance in long-horizon decision-making tasks through multi-step interaction and reasoning at test t
arXiv:2605.14258v1 Announce Type: cross Abstract: Large language models are remarkably capable, yet how computation propagates through their layers remains poorly understood. A growing line of work tr
arXiv:2605.14014v1 Announce Type: cross Abstract: Internet of Things (IoT) systems continuously collect heterogeneous sensing signals from ubiquitous sensors to support intelligent applications such a
arXiv:2605.14742v1 Announce Type: new Abstract: Understanding human--environment interactions from egocentric vision is essential for assistive robotics and embodied intelligent agents, yet existing m
arXiv:2605.14842v1 Announce Type: new Abstract: Humans naturally communicate through abstract concepts like 'mood'. However, current image editing benchmarks focus primarily on explicit, literal comma
arXiv:2605.14629v1 Announce Type: cross Abstract: 3D Gaussian Splatting (3DGS) has emerged as a prominent framework for real-time, photorealistic scene reconstruction, offering significant speed-ups o
arXiv:2605.14434v1 Announce Type: cross Abstract: Generative retrieval offers a promising alternative by unifying the fragmented multi-stage retrieval process into a single end-to-end model. However,
arXiv:2605.14553v1 Announce Type: cross Abstract: Prompt engineering has become central to eliciting the capabilities of large language models (LLMs). At its core lies prompt selection -- efficiently
arXiv:2605.14953v1 Announce Type: new Abstract: We address the problem of conformal selection, where an agent must select a minimal subset of options to ensure that at least one ``success'' is identif
arXiv:2605.13869v1 Announce Type: cross Abstract: Spiking Neural Networks (SNNs), particularly Spiking Transformers, offer energy-efficient processing of event-based sensor data for healthcare applica
arXiv:2605.13942v1 Announce Type: new Abstract: Machine learning (ML) is increasingly applied to optimize system performance in tasks such as resource management and network simulation. Unlike traditi
arXiv:2602.02427v2 Announce Type: replace Abstract: Large language Models (LLMs) have achieved significant breakthroughs across diverse domains; however, they can still produce unreliable or misleadin
arXiv:2605.14833v1 Announce Type: new Abstract: Current language model systems remain fundamentally stateless across sessions, limiting their ability to personalize interactions over time. While retri
arXiv:2605.14589v1 Announce Type: new Abstract: Extending the context window of large language models typically requires training on sequences at the target length, incurring quadratic memory and comp
arXiv:2605.14411v1 Announce Type: cross Abstract: Quadruped robots are often designed with rigid feet to simplify control and maintain stable contact during locomotion. While this approach is straight
arXiv:2510.01172v3 Announce Type: replace Abstract: Large language models (LLMs) require constant updates to remain aligned with evolving real-world knowledge. Model editing offers a lightweight alter
arXiv:2605.14249v1 Announce Type: new Abstract: We present EnergyLens, an end-to-end framework for energy-aware large language model (LLM) inference optimization. As LLMs scale, predicting and reducin
arXiv:2605.14036v1 Announce Type: new Abstract: In current Large Language Models we can trust the production of smoothly flowing prose on the basis of the principles of machine learning. However, ther
arXiv:2510.18326v3 Announce Type: replace Abstract: The rising incidence of natural and human-induced disasters necessitates robust visual recognition systems capable of operating under limited labele
arXiv:2605.14521v1 Announce Type: new Abstract: Layer normalization (LN) is a fundamental component in modern deep learning, but its per-sample centering and scaling introduce non-negligible inference
arXiv:2605.15199v1 Announce Type: cross Abstract: Multi-shot video generation extends single-shot generation to coherent visual narratives, yet maintaining consistent characters, objects, and location
arXiv:2605.14696v1 Announce Type: new Abstract: Data scaling plays a pivotal role in the pursuit of general intelligence. However, the prevailing perception-planning paradigm in autonomous driving rel
arXiv:2605.15179v1 Announce Type: cross Abstract: Scaling Scientific Machine Learning (SciML) toward universal foundation models is bottlenecked by negative transfer: the simultaneous co-training of d
arXiv:2605.13996v1 Announce Type: new Abstract: In robotics, a common challenge in imitation learning is the mismatch between training and deployment conditions, caused, for example, by environmental
arXiv:2605.14750v1 Announce Type: cross Abstract: Large Language Models (LLMs) and Vision Language Models (VLMs) have demonstrated impressive capabilities but remain vulnerable to jailbreaking attacks
arXiv:2605.15042v1 Announce Type: cross Abstract: We propose EverAnimate, an efficient post-training method for long-horizon animated video generation that preserves visual quality and character ident
arXiv:2509.21261v3 Announce Type: replace Abstract: Micro-action Recognition is vital for psychological assessment and human-computer interaction. However, existing methods often fail in real-world sc
arXiv:2605.15171v1 Announce Type: cross Abstract: Disease screening is critical for early detection and timely intervention in clinical practice. However, most current screening models for medical ima
arXiv:2605.14950v1 Announce Type: new Abstract: Vision-Language-Action models have emerged as a promising paradigm for robotic manipulation by unifying perception, language grounding, and action gener
arXiv:2605.13941v1 Announce Type: cross Abstract: Long-term memory is essential for LLM agents that operate across multiple sessions, yet existing memory systems treat retrieval infrastructure as fixe
arXiv:2605.14047v1 Announce Type: new Abstract: Vision Transformers (ViTs) achieve state-of-the-art performance on challenging vision tasks, but their deployment on edge devices is severely hindered b
arXiv:2605.14347v1 Announce Type: new Abstract: We introduce Exemplar Partitioning (EP), an unsupervised method for constructing interpretable feature dictionaries from large language model activation
arXiv:2605.14995v1 Announce Type: new Abstract: Every day, users generate digital traces (e.g., social media posts, chats, and online interactions) that are inherently timestamped and may reflect aspe
arXiv:2605.14153v1 Announce Type: cross Abstract: Exploitation is not a binary event. It is a ladder of acquiring progressive capabilities, from executing a single buggy line of code to taking full co
arXiv:2605.14801v1 Announce Type: new Abstract: Zero-shot vision-and-language navigation (VLN) has gained significant attention due to its minimal data collection costs and inherent generalization. Th
arXiv:2605.14535v1 Announce Type: new Abstract: The increased use of Large Language Models (LLMs) in geography raises substantial questions about the safety of integrating these tools across a wide ra
arXiv:2605.14845v1 Announce Type: new Abstract: Recent advancements in Vision-Language Models (VLMs) have demonstrated strong capabilities in general visual reasoning, yet their applicability to rigor
arXiv:2605.13853v1 Announce Type: cross Abstract: Facial editing is an important task with applications in entertainment, virtual reality, and digital avatars. Most existing approaches rely on generat
arXiv:2602.03417v2 Announce Type: replace Abstract: Large language models hallucinate factual claims and struggle to ground their outputs in retrievable evidence, particularly in non-English languages
arXiv:2605.14305v1 Announce Type: new Abstract: Discrete diffusion language models improve generation efficiency through parallel token prediction, but standard X_0 prediction methods introduce factor
arXiv:2605.14854v1 Announce Type: cross Abstract: Human Mesh Recovery (HMR) is fundamentally ambiguous: under occlusion or weak depth cues, multiple 3D bodies can explain the same image evidence. This
arXiv:2605.14074v1 Announce Type: new Abstract: Fairness in toxicity classification involves three integrated axes: ranking, calibration, and abstention. Training-time interventions and post-hoc safet
arXiv:2605.14665v1 Announce Type: new Abstract: Legal reasoning is not semantic similarity search. A court judgment encodes constrained symbolic reasoning: precedent propagation, procedural state tran
arXiv:2506.04499v2 Announce Type: replace Abstract: Existing LiDAR 3D object detection methods predominantely rely on sparse convolutions and/or transformers, which can be challenging to run on resour
arXiv:2605.14868v1 Announce Type: new Abstract: Generating adversarial examples at scale is a core primitive for robustness evaluation, adversarial training, and red-teaming, yet even 'fast' attacks s
arXiv:2605.14599v1 Announce Type: cross Abstract: We establish novel structural and statistical results for entropy-regularized min-max inverse reinforcement learning (Min-Max-IRL) with linear reward
arXiv:2605.13904v1 Announce Type: cross Abstract: Brain encoder models predict cortical fMRI responses from the internal activations of pretrained vision and language networks, and are typically evalu
arXiv:2605.14590v1 Announce Type: new Abstract: Robust whole-slide image (WSI) analysis under strict data-governance remains challenging due to substantial cross-institutional stain heterogeneity. Dom
arXiv:2605.13974v1 Announce Type: cross Abstract: Diffusion Transformers (DiTs) and related flow-based architectures are now among the strongest text-to-image generators, yet the internal mechanisms t
arXiv:2602.13483v2 Announce Type: replace-cross Abstract: Understanding the internal circuits that language models use to solve tasks remains a central challenge in mechanistic interpretability. A cru
arXiv:2605.14168v1 Announce Type: new Abstract: Learning of continuous exponential family distributions with unbounded support remains an important area of research for both theory and applications in
arXiv:2604.06757v2 Announce Type: replace Abstract: Multimodal generation has long been dominated by text-driven pipelines where language dictates vision but cannot reason or create within it. We chal