Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
Systems for code-mixed (CM) text and speech rarely start from scratch. CM data is scarce, so most work borrows from the languages being mixed, which we call native languages. This transfer can also ru...
Complex chemical systems containing heterogeneous substructures are common in real-world applications. Various physical phenomena of the complex chemical systems are derived from the interactions betw...
Ensuring the alignment of Large Language Models (LLMs) with diverse cultural values is critical for their safe global deployment. However, existing alignment benchmarks are predominantly English-centr...
Modern large-scale cloud systems continuously generate massive and multimodal observability data, such as time-series metrics, log records, and system dependency graphs, which reflect the health state...
Generative reward models (GenRMs) generate natural language rationales to justify preference judgments, yet a correct verdict does not guarantee a sound justification. Existing approaches often rely o...
Code agents increasingly work on evolving real repositories, and memory systems aim to help them reuse earlier experience. However, such experience is diverse and evolving, so it remains unclear how m...
Despite advances in photorealism, semantic fidelity, and aesthetics, text-to-image generation and image editing remain understudied in a human-centered dimension: whether their outputs feel psychologi...
Adapting a forecasting system to a changing world classically means retraining. We ask whether the task of continually learning regimes for time series forecasting can be represented by a piece of tex...
Recent work has explored continuous representations in place of discrete tokens during Chain-of-Thought (CoT) reasoning, often referred to as soft CoT. This is motivated by the idea that a mixture of...
Credit card fraud is a significant problem for financial institutions, resulting in substantial monetary loss each year. Fraud patterns and methods are continuously evolving, with fraudulent transacti...
While LLM agents can generate visually plausible CAD assemblies, these designs often fail to fulfill their intended physical functions. We study functional CAD design, a setting where agents interpret...
In this paper, we systematically investigate the mechanisms, scaling behavior, and generalization of physical Recursive self-improvement. We introduce PhysRSI-eval to quantify physical RSI through a f...
The article "Welcome to Google Gemini 4 Argon" discusses how the new million‑token output window allows users to provide larger inputs to the model in a single pass. It examines benchmark results and cost implications to determine which users will benefit most from this capability.
Sector rotation is a common decision in benchmark-relative portfolio management, where portfolio managers rank sectors for overweight and underweight positions. We formulate this task as ranking secto...
Test-time scaling can improve LLM reasoning, but existing approaches typically adapt generation or apply answer selection after a predetermined generation schedule. We study within-instance allocation...
This paper considers a decision-maker tasked with identifying the $k$ best items from a large pool of candidates, such as job applicants, LLMs, award nominees, or new product ideas. The decision-maker...
Irregular multivariate time series forecasting (IMTSF) requires capturing temporal dynamics and cross-variable dependencies from sparse, asynchronous observations. Existing methods often rely on learn...
Despite rapid advances in large language models (LLMs), their deployment in the sports and health domain remains high-risk due to the absence of domain-specific evaluation benchmarks. Existing general...
Multi-label classification is particularly challenging in streaming scenarios, where data arrives sequentially. Online kernel methods offer a promising solution. However, prevailing methods rely on a...
Fast and reliable manipulation is crucial for practical robot deployment. Although Vision-Language-Action (VLA) models have recently shown remarkable progress as generalist robot policies, their execu...