The rapid proliferation of AI-generated visual media has created an urgent need for efficient, trustworthy deepfake detection systems. However, existing deep le...
Physical computing systems provide a promising route toward hardware-native machine learning, but their computational capabilities remain difficult to character...
Existing neural combinatorial optimization solvers frame solution search as imitation of optimal decisions, inherently limiting their utility to single-objectiv...
Multiview 3D evaluation assumes that the images being scored are observations of one static 3D scene. This assumption can fail in NVS and sparse-view reconstruc...
Current hierarchical attention methods, such as NSA and InfLLMv2, select the top-k relevant key-value (KV) blocks based on coarse attention scores and subsequen...
Pipeline parallelism is a key technique for scaling large-model training, but modern workloads exhibit runtime variability in computation and communication. Exi...
Modern audio generation predominantly relies on latent-space compression, introducing additional complexity and potential information loss. In this work, we cha...
Recent video editing models have converged on a unified conditioning design: a single diffusion transformer jointly consumes text, source video, and reference i...
Recent large language models (LLMs) have demonstrated strong capabilities in understanding and generating code, from competitive programming to repository-level...
Spatial intelligence unfolds through a perception-action loop: agents act to acquire observations, and reason about how observations vary as a function of actio...
Diffusion-based generative models increasingly rely on inference-time guidance, adding a drift term or reweighting mixture of experts, to improve sample quality...
Inspired by the emergent behaviors in large language models that generalized human intelligence, the research community is pursuing similar emergent capabilitie...
Multimodal Large Language Models (MLLMs) still struggle with fine-grained visual understanding, where answers often depend on small but decisive evidence in the...
We present LongLive-2.0, an NVFP4-based parallel infrastructure throughout the full training and inference workflow of long video generation, addressing speed a...
Medicine is inherently pluralistic. Principles such as autonomy, beneficence, nonmaleficence, and justice routinely conflict, and such ethical dilemmas often sh...
Diffusion models have been shown to implicitly generate visual content autoregressively in the frequency domain, where low-frequency components are generated ea...
We present PIXLRelight, a feed-forward approach for physically controllable single-image relighting. Existing methods either provide limited lighting control (e...
Egocentric memory is widely used in embodied intelligence, but it may be insufficient for comprehensive spatial-temporal reasoning. Inspired by human recall fro...
Autoregressive video generation has improved rapidly in visual fidelity and interactivity, but it still suffers from long-term inconsistency and memory degradat...
While scaling laws govern aggregate large language model performance, no scaling law has linked factual recall to both model size and training-data composition....
Evaluating embodied systems on real dexterous hardware requires more than isolated primitive skills: an agent must perceive a changing tabletop scene, choose a ...
Post-training has split large language model (LLM) alignment into two largely disconnected tracks. Online reinforcement learning (RL) with verifiable rewards dr...
Unified multimodal models (UMMs) strive to consolidate visual understanding and visual generation within a single architecture. However, prevailing training par...
With the wide adoption of Multimodal Models (MMs) in real-world scenarios, it is significant to efficiently train emerging MMs that exhibit increasingly complex...
Population protocols are a model of distributed computing where n agents, each a simple finite-state machine, interact in pairs to solve a common task against a...
Unmanned Aerial Vehicles in dynamic environments face telemetry outages, structural vibrations, and regime-dependent noise that invalidate the stationary covari...
Equipping LLMs with tool-use capabilities via Agentic Reinforcement Learning (Agentic RL) is bottlenecked by two challenges: the lack of scalable, robust execut...
Tabular foundation models (TFMs) achieve strong performance on health datasets, but their inference cost and infrastructure requirements limit practical use. We...
Compound AI applications, which compose calls to ML models using a general-purpose programming language like Python, are widely used for a variety of user-facin...
Legacy systems concentrate business rules, architectural decisions, and operational exceptions that often remain implicit in code, data, configuration, and main...
In-Network Collective (INC) acceleration holds immense potential for optimizing AI training and inference; however, its cross-layer nature has historically hind...
Major deployed generative AI advertising systems preserve a visible boundary between commercial content and AI-generated responses. Yet empirical research shows...
As LLM benchmarks saturate, the evaluation community has pursued two strategies to increase difficulty: escalating knowledge demands (GPQA, HLE) or removing kno...
Central to human-aligned AI is understanding the benefits of human-elicited labels over synthetic alternatives. While human soft-labels improve calibration by c...
The distributed setting for Saddle Problems (SPs) has recently emerged as a framework for various modern applications in machine learning and multiagent systems...
Coding agents now run autonomously with shell, file, and network privileges. When a user issues a benign request, the agent sometimes does more than asked: it d...
In retrieval-augmented coding, failures often begin when the relevant file is absent from the retrieved context. Under frozen generic tokenization, where a BM25...
The brain learns abstract representations of high-dimensional sensory input, but the plasticity rules that enable such learning are unknown. We study biological...
Sparse matrix-vector multiplication (SpMV) is crucial in computational science, engineering, and machine learning. Despite substantial efforts to improve SpMV p...
AI tools are enabling engineers to absorb roles previously distributed across cross-functional squads, yet there is little structured evidence on how to design ...
This work presents a novel variant of the Firefly Algorithm (FA) for data clustering, addressing limitations of traditional methods like K-Means that struggle w...
Vehicular edge computing (VEC) enables latency-sensitive vehicular applications by offloading computation-intensive tasks to nearby edge servers. However, real-...
This paper presents a novel method to compare two numbers in Residue Number System (RNS) using an additional modulus, which is often already available because i...
Multimodal optimization requires finding many optima rather than merely keeping a diverse population. Yet most niching-based evolutionary algorithms rely on dis...
Behavioral studies of LLM-based software engineering agents extract operational rules about which trajectory shapes correlate with higher resolution rates: that...
Software repositories accumulate large amounts of unstructured knowledge in commit messages, pull-request discussions, and issue threads, but developers and AI ...
Real-time magnetic resonance imaging (rtMRI) of speech production enables non-invasive visualization of dynamic vocal-tract motion and is valuable for speech sc...
Collecting large-scale egocentric video datasets with dense spatial and temporal annotations is costly, slow, and often constrained by environmental biases, pri...
