Large language models (LLMs) exhibit systematic political bias across a variety of sensitive contexts. We find that LLMs handle counterpart topics from opposing...
Large language models (LLMs) are typically trained on shuffled corpora, yielding models whose knowledge is frozen at train time and whose temporal grounding rem...
Every Python function deployed as an LLM tool must today exist in two forms: an HTTP endpoint for human-facing clients and CI pipelines, and an MCP tool registr...
We investigate whether acoustic emotion recognition models can serve as proxies for the Pathos dimension in political speech analysis, as operationalised by the...
As wearable and mobile devices become increasingly embedded in daily life, they offer a practical way to continuously sense human motion in the wild. But inerti...
Large language models are routinely used as automated evaluators: to review code, moderate content, or score outputs, often with many items passing through one ...
Skills are increasingly used to package agent instructions, workflows, scripts, and reference materials. In enterprise settings, however, skills often need to e...
The advent of cardless artificial intelligence (AI) banking heralds a paradigm shift in the financial landscape, offering users unprecedented security and conve...
Today, tool-calling agents are commonly evaluated or tested on static datasets of execution traces, including input commands, agent responses, and associated to...
Hybrid language models like Jamba mix attention layers with State Space Models (SSMs), creating two memory cache types with opposite profiles: Key-Value (KV) ca...
Does the relationship between learning rules and brain alignment generalize across species? We extend our prior finding that untrained CNNs match backpropagatio...
As large language models (LLMs) are increasingly deployed for software engineering, constructing high-quality benchmarks is crucial for evaluating not just the ...
Despite strong predictive results in the clinical machine learning literature, the translation of these models into bedside use remains limited by systems-level...
The Thousand Brains Theory (TBT) and its open-source Monty framework model object recognition through sensorimotor inference -- identifying objects by actively ...
The advent of edge computing has enabled resource-constrained clients to delegate intensive computational tasks to distributed edge servers, especially within I...
The integration of machine learning with domain-specific physics is transforming the design, monitoring, and control of electricity systems, where data scarcity...
We develop a mean-field theory of dropout as a perturbation of critical signal propagation at the edge of chaos. Dropout shifts the perfect-alignment fixed poin...
Pretrained diffusion models serve as frozen teachers feeding downstream pipelines such as text-to-3D, single-step distillation, and data attribution. The teache...
Scaling test-time compute by iteratively updating a latent state has emerged as a powerful paradigm for reasoning. Yet the internal mechanisms that enable these...
Hyperparameter transfer allows extrapolating optimal optimization hyperparameters from small to large scales, making it critical for training large language mod...
Equivariant graph neural network (GNN) methods for antibody complementarity-determining region (CDR) design achieve the highest sequence recovery but suffer fro...
Precise measurement of the kinematic Sunyaev-Zel'dovich (kSZ) effect - a probe of the large-scale distribution of baryonic matter, a key observable for cosmolog...
Recent advances in artificial intelligence (AI) have accelerated the growth of both human-authored and AI-generated research outputs, placing increasing strain ...
Deep research, in which an agent searches the open web, collects evidence, and derives an answer through extended reasoning, is a prominent use case for frontie...
Visual Question Answering (VQA) benchmarks have largely emphasized perception-based tasks that can be solved from visual content alone. In contrast, many real-w...
Relational prediction tasks are fundamental in many real-world applications, where data are naturally stored in relational databases (RDBs). Relational Deep Lea...
Computer-use agents (CUA) automate tasks specified with natural language such as 'order the cheapest item from Taco Bell' by generating sequences of calls to to...
Reinforcement learning with verifiable rewards (RLVR) has become a dominant paradigm for improving reasoning in large language models (LLMs), yet the underlying...
Reinforcement learning from verifiable rewards (RLVR) has emerged as a central technique for improving the reasoning capabilities of large language models. Desp...
We present Mem-π, a framework for adaptive memory in large language model (LLM) agents, where useful guidance is generated on demand rather than retrieved from ...
Autonomous manipulation systems have achieved remarkable capabilities, yet the integration of human expertise with diffusion-based policies in shared control re...
Suppose a planner has a pre-trained simulator of a sequential decision problem and the option to run real experiments in the field. The simulator is cheap to qu...
As AI agents increasingly contribute to code development and maintenance, there is still limited empirical evidence on the quality and risk characteristics of t...
Universal approximation theorems provide a mathematical explanation for the expressive power of neural networks. They assert that, under mild conditions on the ...
Vision-language models (VLMs) are increasingly being explored for video game quality assurance, especially gameplay glitch detection. Most existing evaluations,...
Large language model (LLM) inference has become a dominant workload in modern data centers, driving significant GPU utilization and energy consumption. While pr...
Third-party Python libraries introduce dependency management overhead, supply chain risk, and deployment friction in constrained environments. A natural questio...
As long-horizon coding agents produce more code than any developer can review, oversight collapses onto a single surface: the automated test suite. Reward hacki...
In The Algebraic Mind, Gary Marcus identified three components essential for any adequate cognitive architecture: operations over variables, recursively structu...
In The Algebraic Mind, Gary Marcus identified three components essential for any adequate cognitive architecture: operations over variables, recursively structu...
Diagnosing failures in LLM agents remains largely manual. Practitioners inspect a small subset of execution traces, form ad-hoc hypotheses, and iterate. This pr...
Modern LLM serving is no longer homogeneous or monolithic. Production systems now combine disaggregated execution, complex parallelism, runtime optimizations, a...
Federated learning (FL) has emerged as a promising paradigm for managing electric vehicle (EV) battery data in intelligent transportation systems (ITS), enablin...
A recent trend is to leverage machine learning models to improve the evolutionary design and optimization process. We propose a novel transformer-based mutation...
AlltoAll dispatch is the dominant bottleneck of MoE expert parallelism, and the interconnect community has responded with four families of mitigations: predicti...
Communication is a major bottleneck in distributed learning, especially in large-scale settings and in federated learning environments with slow links. Three st...
Among all of the possible chemical compounds, it’s estimated that between 10²⁰ and 10⁶⁰ may hold potential as small‑molecule drugs. Evaluating each of those com...
Transformers trained on modular arithmetic exhibit sharp transitions between memorization, generalization, and collapse. We show that weight decay acts as a sca...
