Can an MLP Absorb Its Own Skip Connection?
arXiv:2604.23705v1 Announce Type: new Abstract: We study when a skip connection around a single-hidden-layer MLP can be absorbed into a residual-free MLP of the same width. We first show that for any
Knowledge catalogue
arXiv:2604.23705v1 Announce Type: new Abstract: We study when a skip connection around a single-hidden-layer MLP can be absorbed into a residual-free MLP of the same width. We first show that for any
arXiv:2604.23471v1 Announce Type: cross Abstract: This study asks whether the threat of AI detection changes how people write with AI, and whether other people can tell the difference. In a two-phase
arXiv:2604.24444v1 Announce Type: new Abstract: Despite the growing use of large language models (LLMs) for writing tasks, users may hesitate to rely on LLMs when personal style is important. Post-edi
arXiv:2601.06352v2 Announce Type: replace Abstract: Adapting large language models to individual users remains challenging due to the tension between fine-grained personalization and scalable deployme
arXiv:2604.23876v1 Announce Type: new Abstract: We present Cardiac Stability Theory (CST), an axiomatically grounded framework formally defining cardiovascular health as a stability margin around a ca
arXiv:2604.23718v1 Announce Type: new Abstract: As dental caries appear as subtle, low-contrast lesions in intraoral imaging, existing deep learning models face significant challenges in the early det
arXiv:2604.23628v1 Announce Type: cross Abstract: Hierarchical clustering is a fundamental task in data analysis, yet for a long time it lacked a principled objective function. Dasgupta [STOC 2016] in
arXiv:2604.24447v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models are promising for generalist robot control, but on-robot deployment is bottlenecked by real-time inference under t
arXiv:2510.13312v2 Announce Type: replace Abstract: We present ChatR1, a reasoning framework based on reinforcement learning (RL) for conversational question answering (CQA). Reasoning plays an import
arXiv:2604.22989v1 Announce Type: cross Abstract: Recent medical multimodal foundation models are built as multimodal LLMs (MLLMs) by connecting a CLIP-pretrained vision encoder to an LLM using LLaVA-
arXiv:2604.16922v2 Announce Type: replace Abstract: Climate research is pivotal for mitigating global environmental crises, yet the accelerating volume of multi-scale datasets and the complexity of an
arXiv:2604.05500v2 Announce Type: replace Abstract: Nighttime image dehazing faces a more complex degradation pattern than its daytime counterpart, as haze scattering couples with low illumination, no
arXiv:2601.22301v2 Announce Type: replace Abstract: Traditional rendering pipelines rely on complex assets, accurate materials and lighting, and substantial computational resources to produce realisti
arXiv:2509.11717v5 Announce Type: replace-cross Abstract: Text-guided sound separation enables flexible audio editing, assistive listening, and open-domain source extraction, but systems such as Audio
arXiv:2604.24634v1 Announce Type: cross Abstract: Light-activated drugs are a promising way to treat localized diseases for which existing treatments have severe side effects. However, their developme
arXiv:2604.23952v1 Announce Type: cross Abstract: Stochastic reduced-order models are widely used to represent the effective dynamics of complex systems, but estimating their drift and diffusion coeff
arXiv:2604.22787v1 Announce Type: cross Abstract: Africa's green industrialization imperative demands reliable infrastructure for monitoring air quality. We present a satellite-reanalysis PM2.5 fusion
arXiv:2309.00578v2 Announce Type: replace Abstract: In the context of unsupervised learning, Lloyd's algorithm is one of the most widely used clustering algorithms. It has inspired a plethora of work
arXiv:2604.22801v1 Announce Type: cross Abstract: It is a challenging task to forecast equity prices in fast moving financial markets as this becomes even more difficult when the predictive signal is
arXiv:2604.24693v1 Announce Type: new Abstract: Linear activation steering is a powerful approach for eliciting the capabilities of large language models and specializing their behavior using limited
arXiv:2604.23987v1 Announce Type: new Abstract: Continual learning for large language models is typically evaluated through accuracy retention under sequential fine-tuning. We argue that this perspect
arXiv:2410.13903v3 Announce Type: replace-cross Abstract: Proprietary large language models (LLMs) exhibit strong generalization capabilities across diverse tasks and are increasingly deployed on edge
arXiv:2604.24170v1 Announce Type: new Abstract: Concept Bottleneck Models (CBMs) predict through human-interpretable concepts, but they typically output point concept probabilities that conflate epist
arXiv:2604.24361v1 Announce Type: new Abstract: Large language models (LLMs) have achieved strong performance in general machine translation, yet their ability in culture-aware scenarios remains poorl
arXiv:2604.23693v1 Announce Type: new Abstract: Heterogeneous multi-robot systems feature significant adaptability for complex environments. However, effective collaboration that fully exploits the ro
arXiv:2604.22909v1 Announce Type: new Abstract: Understanding and representing complex climate variability is essential for both scientific analysis and predictive modeling. However, identifying meani
arXiv:2604.24647v1 Announce Type: cross Abstract: Long-context reasoning is a critical capability of large language models (LLMs), enabling applications such as long-document understanding, summarizat
arXiv:2604.23976v1 Announce Type: new Abstract: The sense of family connectedness may support positive outcomes including individual well-being, resilience, and healthy family functioning. However, as
arXiv:2601.02455v2 Announce Type: replace-cross Abstract: Deploying Automatic Speech Recognition (ASR) models on memory-constrained edge devices requires aggressive low-bit weight quantization. Layer-
arXiv:2604.24547v1 Announce Type: new Abstract: Progression to dialysis or end-stage renal disease is a rare but clinically important outcome. Clinicians need evidence on how medication exposures infl
arXiv:2604.24719v1 Announce Type: new Abstract: Segmentation models such as Segment Anything Model (SAM) and SAM2 achieve strong prompt-driven zero-shot performance. However, their training on natural
arXiv:2604.24692v1 Announce Type: new Abstract: We propose Noise-Based Spectral Embedding (NBSE), a physics-informed framework for selecting informative features from high-dimensional data without gre
arXiv:2604.24575v1 Announce Type: new Abstract: Diffusion models are primarily trained for image synthesis, yet their denoising trajectories encode rich, spatially aligned visual priors. In this paper
arXiv:2604.23636v1 Announce Type: new Abstract: In this work, we study Source-Free Unsupervised Domain Adaptation under corruption-induced domain shifts, where performance degradation is caused by nat
arXiv:2511.21715v2 Announce Type: replace-cross Abstract: This paper argues that dataset structure is important in image recognition tasks (among other tasks). Specifically, we focus on the nature and
arXiv:2505.13975v4 Announce Type: replace Abstract: While Large Reasoning Models (LRMs) have demonstrated success in complex reasoning tasks through long chain-of-thought (CoT) reasoning, their infere
arXiv:2604.24663v1 Announce Type: cross Abstract: We study finite-horizon quadratic control of linear systems with bilinear observations, in which the control input affects not only the state dynamics
Earlier this month, an Erdős problem that had been open for 60 years was solved with help from GPT-5.4 Pro. What happens now that AI is getting good at math? OpenAI researchers @SebastienBubeck and @E
arXiv:2603.10926v1 Announce Type: cross Abstract: Time-series anomaly detectors are commonly compared on workstation-class hardware under unconstrained execution. In-vehicle monitoring, however, requi
arXiv:2604.23763v1 Announce Type: new Abstract: Large diffusion transformers (DiTs) follow global editing instructions well but consistently leak local edits into unrelated regions, because joint-atte
arXiv:2604.22992v1 Announce Type: new Abstract: Reliable object perception is necessary for general-purpose service robots. Open-vocabulary detectors struggle to generalize beyond a few classes and fu
arXiv:2604.24555v1 Announce Type: new Abstract: We consider online learning problems under a partial observability model capturing situations where the information conveyed to the learner is between f
arXiv:2604.23172v1 Announce Type: new Abstract: In this work, we developed and tested 3 techniques for vector quantization (VQ) based model weight compression. To mitigate codebook collapse and enable
arXiv:2604.23532v1 Announce Type: cross Abstract: Short-term human pose prediction plays a crucial role in interactive systems, assistive robots, and emotion-aware human-computer interaction[1-3]. Whi
arXiv:2601.00823v2 Announce Type: replace Abstract: Large reasoning models (LRMs) have heterogeneous inference energy costs based on which model is used and how much it reasons. To reduce energy, it i
arXiv:2604.23426v1 Announce Type: new Abstract: Federated learning (FL) is a distributed machine learning method where multiple devices collaboratively train a model under the management of a central
arXiv:2604.24563v1 Announce Type: cross Abstract: Machine-learning interatomic potentials (MLIPs) have enabled molecular dynamics at near ab initio accuracy, yet remain limited to energies and forces
arXiv:2604.22776v1 Announce Type: cross Abstract: A chef's intuition about flavor, texture, and cultural identity represents tacit knowledge that is difficult to articulate yet central to culinary pra
arXiv:2604.22855v1 Announce Type: new Abstract: The core objective of image captioning is to achieve lossless semantic compression from visual signals into textual modalities. However, the reliance on
arXiv:2510.02629v3 Announce Type: replace Abstract: Context utilisation, the ability of Language Models (LMs) to incorporate relevant information from the provided context when generating responses, r
arXiv:2604.23887v1 Announce Type: cross Abstract: LLM-powered applications routinely embed secrets in system prompts, yet models can be tricked into revealing them. We built an adaptive attacker that
arXiv:2406.14075v2 Announce Type: replace Abstract: It is crucial to understand a specific domain by events. Extensive event extraction research has been conducted in many domains such as news, financ
arXiv:2505.17855v2 Announce Type: replace Abstract: Understanding sources of a model's uncertainty regarding its predictions is crucial for effective human-AI collaboration. Prior work proposes using
arXiv:2604.23260v1 Announce Type: cross Abstract: An approach to construct explicit integral representations for two-layer ReLU networks is presented, which provides relatively simple representations
arXiv:2604.23860v1 Announce Type: cross Abstract: Egocentric videos provide a distinctive setting in which sound serves as crucial cues to understand user activities and surroundings, particularly whe
arXiv:2501.02673v4 Announce Type: replace Abstract: Having a sufficient quantity of quality data is a critical enabler of training effective machine learning models. Being able to effectively determin
arXiv:2604.23562v1 Announce Type: cross Abstract: The relationship between brain lateralization and cognitive functions is well-documented. The left hemisphere primarily handles tasks such as language
arXiv:2604.24103v1 Announce Type: new Abstract: Federated learning (FL) offers a promising distributed learning paradigm for internet of vehicles (IoV) applications. However, it faces challenges from
arXiv:2604.24012v1 Announce Type: new Abstract: Federated learning enables a population of clients to collaboratively train machine learning models without exchanging their raw data, but standard algo
arXiv:2604.24397v1 Announce Type: cross Abstract: In the noisy intermediate-scale quantum (NISQ) regime, quantum devices contain hardware-specific noise sources which restrict device-invariant error m