MIT‑led Institute for Artificial Intelligence and Fundamental Interactions IAIFI receives renewed NSF support The Institute for Artificial Intelligence and Fund...
Thursday June 4, 2026 4:24 am PDT by Tim Hardwickhttps://www.macrumors.com/author/tim-hardwick/ Apple has published a new adhttps://www.youtube.com/watch?v=Spb-...
Training Data Attribution (TDA) seeks to trace a model's predictions back to its training data. The gold standard for TDA relies on causal interventions, observ...
Multi-agent reasoning systems adopt a 'generate-then-transfer' paradigm that forces end-to-end latency to scale linearly with pipeline depth. We introduce Strea...
Reasoning models have advanced rapidly, but the dominant reinforcement learning from verifiable rewards (RLVR) recipe remains surprisingly narrow: sample many r...
The radial basis function neural network (RBFN) trained with a gradient descending algorithm provides an effective fully connected structure in both shallow and...
Vehicle body type is a significant determinant of cyclist injury severity in overtaking crashes, yet automated tools for classifying vehicles into injury-risk-r...
When post-trained language models fail on reasoning problems, the common test-time-scaling response is to spend more compute on additional attempts, and the fai...
Recent developments in multi-view image editing with generative models have brought us a step closer toward general 3D content generation and customization. Mos...
The rapid advancement of high-throughput sequencing has led to large, high-dimensional omics datasets. Deep unsupervised learning architectures, particularly Au...
Generating realistic financial time series is challenging as training data is often limited to a single historical path. With such scarce data, overfitting is h...
Deep active learning has previously been explored for LLM in-context sample selection, but not with methods that utilise recent advances in understanding of tra...
Koopman theory turns nonlinear dynamics into a linear spectral problem. In computation, however, everything depends on a hard finite-dimensional choice: the obs...
Individual-level mobility prediction is central to urban simulation, transportation planning, and policy analysis. Supervised sequence models achieve strong acc...
Preserving data privacy is an important topic in structural data management and data mining. However, the issue of privacy leakage in distributed causal structu...
After the success of 3D Gaussian Splatting (3DGS) for novel view synthesis, many works have explored how to also use it for geometric surface representation. Ho...
Audio is an inherently interactive modality, yet today's Large Audio Language Models (LALMs) are offline, and streaming audio models each handle only a single t...
Children learn the meanings of words from a continuous, temporally structured stream of egocentric experience. Recent work shows that neural networks can also l...
We propose a label-free approach to adapt powerful but generic vision foundation models to specialized scientific domains. Standard supervised fine-tuning is of...
We investigate whether methods of human mathematics pedagogy can guide the training of language models toward arithmetic reasoning. Building on the GASING metho...
The Nancy Grace Roman Space Telescope (Roman), set for launch as early as September 2026, will conduct wide-field infrared imaging surveys with unprecedented sp...
When an AI agent calls an API and hits a validation error, it needs more than what went wrong -- it needs what to do next. A self-reflective API returns, on val...
AI tools for programming are no longer just autocomplete or chat assistants: they organize themselves as development frameworks, with process, roles, artifacts ...
Optimizing urban layouts for climate adaptation requires balancing building density with cold-air ventilation. Because physics-based climate simulations are com...
LLM serving frameworks are quickly evolving with a complex software stack and a vast number of optimizations. The rapid development process can introduce silent...
Speculative inference (SPIN) was originally developed as an efficient architecture to accelerate Large Language Models (LLMs). In this work, we propose its dist...
This study aims to determine whether the application of Deep Reinforcement Learning (DRL) as a specialized execution overlay can enhance pair trading in highly ...
Offline multi-objective optimization (Offline MOO) aims to discover novel Pareto-optimal designs based on static datasets without expensive environment interact...
Speculative decoding accelerates autoregressive large language model inference by drafting multiple tokens and verifying them in a single target-model forward p...
We investigate whether neuron populations within neural networks evolve predictably with scale, extending scaling laws beyond macroscopic observables such as lo...
The ability to train spiking neural networks is essential for modeling biological neural networks as well as for neuromorphic computing. However, for the extens...
Urban traffic simulation is a critical tool for infrastructure planning, including the placement of electric vehicle charging stations. However, realistic traff...
Signed spiking neurons carry richer information than standard spiking neurons. This work proposes a compact magnetic tunnel junction (MTJ)-based neuron for sign...
Equilibrium Propagation (EP) is a physics-based training framework that has primarily been employed in energy-based models, including continuous Hopfield networ...
The large sizes of Spiking Vision Transformers (SViTs) still hinder their embedded implementation, highlighting the need for model compression. State-of-the-art...
Recent multimodal large language models have demonstrated strong reasoning ability, yet their reliability as automated evaluators remains limited by a critical ...
Multimodal Large Language Models (MLLMs) achieve strong performance through instruction tuning, but real-world deployment requires them to continually acquire n...
Video is temporally redundant: adjacent frames usually share most objects, background, and layout. Yet existing video multimodal large language models (video ML...
Clinical practice is not the selection of an answer from enumerated options: a physician gathers heterogeneous information incrementally and commits to sequenti...
Heterogeneous Differential Privacy (HDP) in Federated Learning (FL) allows clients to select individual privacy budgets (varepsilon_i) according to institutiona...
Autonomous robots that interact with people must make safe and efficient decisions under human-induced uncertainty, such as their preferences, goals, competency...
Post-training compression of Large Language Models (LLMs) removes entire architectural components, either deleting them or replacing them with fitted modules. E...
Despite advances in depth estimation, flying points remain a persistent failure mode: near object boundaries, depth estimators often predict spurious 3D points ...
Diffusion large language models (dLLMs) have recently emerged as a promising alternative to autoregressive (AR) LLMs, offering faster inference through parallel...
Text files such as skill files, memory files, and behavioral configuration files play a central role in defining how modern agents act. Through edits by humans ...
Aligning Large Language Models (LLMs) with human values often degrades their general capabilities, termed the alignment tax. Existing methods mitigate this by b...
Long-tailed recognition poses a significant challenge for deep learning. The two-stage decoupling paradigm, which separates representation learning from classif...
Agentic systems entering production typically operate as partially integrated assemblies where structural defects, not task-level errors, dominate the failure l...
