Contrastive language-image pretraining (CLIP) suffers from two structural weaknesses: the symmetric InfoNCE loss discards the relative ordering among unmatched ...
Estimating camera geometry typically involves solving minimal problems formulated as systems of multivariate polynomial equations, which often pose computationa...
The rapid expansion of the Internet of Things (IoT) and Industrial IoT (IIoT) has created a massive, heterogeneous attack surface that challenges traditional ne...
Large language models have achieved remarkable success under the autoregressive paradigm, yet high-quality text generation need not be tied to a fixed left-to-r...
Evaluative claims about LLM infrastructure -- ``workload X is fastest on hardware Y with software Z'' -- depend on a complex configuration space spanning hardwa...
Agentic reinforcement learning (RL) has emerged as a key driver for improving the multi-step reasoning and tool-use capabilities of LLMs. However, its efficienc...
LLM-based autonomous coding agents have reshaped software development. While these agents excel at code generation, open questions persist about the long-term m...
Large Language Model (LLM) agents demonstrate strong performance in autonomous code generation under loose specifications. However, production-grade software re...
Spatio-temporal Bayesian inference drives environmental and health sciences using latent Gaussian models. Integrated Nested Laplace Approximations (INLA) enable...
A hallmark of life on Earth is the ability of agents to exert causal power and be drivers of subsequent events. This is key to cognition at all scales. Causal e...
Hybrid parallelism underpins large-scale LLM training across tens of thousands of GPUs. At such scale, hardware failures on individual devices lead to performan...
Large language model systems are increasingly deployed as agentic workflows that interleave reasoning, tool use, memory, and iterative refinement. These systems...
Many real-world optimization problems consist of multiple tightly coupled subproblems whose solutions must be coordinated to achieve high overall performance. H...
Large language models (LLMs) are now largely involved in software development workflows, and the code they generate routinely includes third-party library (TPL)...
As large models evolve from conversational assistants into autonomous agents, challenges increasingly arise from long-horizon decision making, tool use, and rea...
Developers often make similar mistakes across code locations implementing related functionalities. These locations, called siblings, share similar issues and re...
We introduce an evaluation framework of 500 C verification tasks across five property types (memory safety, overflow, termination, reachability, data races) bui...
Background: Open source software ecosystems exhibit dense dependency networks in which maintenance degradation of structurally central packages can propagate wi...
LLM-as-a-Judge pipelines have become the de facto evaluator for agent safety, yet existing benchmarks treat their verdicts as ground-truth proxies without check...
Most coding-agent benchmarks ask whether generated code behaves correctly. That remains essential, but repository-level engineering is increasingly agent-manage...
As production code evolves, the test suite must co-evolve to remain effective. Existing benchmarks for test evolution operate at method-level granularity with p...
We present TACO, a toolsuite for the development and automatic verification of fault-tolerant and threshold-based distributed algorithms. Our toolsuite implemen...
Data-parallel (DP) load balancing has emerged as a first-order bottleneck in large-scale LLM serving. When a model is sharded across devices via tensor parallel...
For years, we have built LLM serving systems like any other critical infrastructure: a single general-purpose stack, hand-tuned over many engineer-years, meant ...
Peak breaking Matrix Multiplication is a promising technique to improve the performance of DL, especially in LLM training and inference. We present FalconGEMM, ...
High-capacity associative memory models, such as Kernel Logistic Regression (KLR) Hopfield networks, have demonstrated strong storage capabilities but typically...
Linear Attention (LA) offers a promising paradigm for scaling large language models (LLMs) to long sequences by avoiding the quadratic complexity of self-attent...
We introduce Graph Normalization (GN), a principled dynamical system on graphs that serves as a differentiable approximation engine for the NP-hard Maximum Weig...
Dense 3D reconstruction and tracking of dynamic scenes from monocular video remains an important open challenge in computer vision. Progress in this area has be...
We study outlier tokens in Diffusion Transformers (DiTs) for image generation. Prior work has shown that Vision Transformers (ViTs) can produce a small number o...
The landscape of high-performance image generation models is currently shifting from the inefficient multi-step ones to the efficient few-step counterparts (e.g...
This study presents a novel deterministic optimization algorithm based on a special variant of the Linear Congruential Generator (LCG). While conventional algor...
Grammaticality and likelihood are distinct notions in human language. Pretrained language models (LMs), which are probabilistic models of language fitted to max...
In this note, we report five mathematical discoveries made in collaboration with Grok, all of which have been subsequently verified by the authors. These includ...
Carbery proposed the following sharpened form of triangle inequality for many functions: for any pge 2 and any finite sequence (f_j)_jsubset L^p we have [ Big|s...
Long-horizon search agents must manage a rapidly growing working context as they reason, call tools, and observe information. Naively accumulating all intermedi...
How many key-value associations can a dtimes d linear memory store? We show that the answer depends not only on the d^2 degrees of freedom in the memory matrix,...
This paper reports on the LoViF 2026 PhyScore challenge, a competition on holistic quality assessment of world-model-generated videos across both 2D and 4D gene...
Deep search has become a crucial capability for frontier multimodal agents, enabling models to solve complex questions through active search, evidence verificat...
By far the most common way to estimate an expected loss in machine learning is to draw samples, compute the loss on each one, and take the empirical average. Ho...
Pre-trained transformers are able to learn from examples provided as part of the prompt without any weight updates, a remarkable ability known as in-context lea...
Background: Existing MRI LLM benchmarks rely mainly on review-book multiple-choice questions, where top proprietary models already score highly, limiting discri...
Behavior Cloning (BC) has emerged as a highly effective paradigm for robot learning. However, BC lacks a self-guided mechanism for online improvement after demo...
Driven by a rapid co-evolution of both harness and underlying models, LLM agents are improving at a dizzying pace. In our prior work (performed in Dec. 2025), w...
Self-consistency detects hallucinations by generating multiple sampled answers to a question and measuring agreement, but this requires repeated decoding and ca...
Evolutionary computation has long promised to deliver both high-performance optimization tools as well as rigorous scientific simulations of Darwinian evolution...
Accurate analysis of histopathological images is critical for disease diagnosis and treatment planning. Whole-slide images (WSIs), which digitize tissue specime...
Synthesizing physics-grounded 3D assets is a critical bottleneck for interactive virtual worlds and embodied AI. Existing methods predominantly focus on static ...
