Elon Musk's so-called Department of Government Efficiency has deployed a proprietary chatbot called GSAi to 1,500 federal workers at the General Services Administration, WIRED has confirmed. The move to automate tasks previously done by humans comes as DOGE continues its purge of the federal workforce. GSAi is meant to support "general" tasks, similar to commercial tools like ChatGPT or Anthropic's Claude. It is tailored in a way that makes it safe for government use, a GSA worker tells WIRED. The DOGE team hopes to eventually use it to analyze contract and procurement data, WIRED previously reported.

Paolo Ardoino, CEO of the cryptocurrency company Tether, was flying over Switzerland last week as he contemplated the changing regulatory landscape. Tether used to be at war with the establishment. Now it is the establishment. The crypto giant – tether is the most traded cryptocurrency in the world – has had a strange trip. Four years ago, banks were dropping Tether as a client, and regulators in New York had the company against the wall over questions about commingled client and corporate funds.

Symmetry rules that atoms obey when they bond together to form an ordered crystal play a fundamental role in determining their physical, chemical, and electronic properties such as electrical and thermal conductivity, optical and polarization behavior, and mechanical strength. Almost all known crystalline materials have internal symmetry. Consistently generating stable crystal structures is still an open challenge, specifically because such symmetry rules are not accounted for. To address this issue, we propose WyFormer, a generative model for materials conditioned on space group symmetry. We use Wyckoff positions as the basis for an elegant, compressed, and discrete structure representation. To model the distribution, we develop a permutation-invariant autoregressive model based on the Transformer and an absence of positional encoding. WyFormer has a unique and powerful synergy of attributes, proven by extensive experimentation: best-in-class symmetry-conditioned generation, physics-motivated inductive bias, competitive stability of the generated structures, competitive material property prediction quality, and unparalleled inference speed.

As video language models (VLMs) gain more applications in various scenarios, the need for robust and scalable evaluation of their performance becomes increasingly critical. The traditional human expert-based evaluation of VLMs has limitations in consistency and scalability, which sparked interest in automatic methods such as employing VLMs to evaluate VLMs. However, the reliability of VLMs as judges remains underexplored. Existing methods often rely on a single VLM as the evaluator. However, this approach can be unreliable or biased because such a model may lack the ability to fully understand the content and may have inherent biases, ultimately compromising evaluation reliability. A remedy is to apply the principle of collective thoughts, aggregating evaluations from multiple VLMs to enhance reliability. This study investigates the efficacy of such approaches, particularly when the pool of judges includes both reliable and unreliable models. Our findings reveal that incorporating collective judgments from such a mixed pool does not necessarily improve the accuracy of the final evaluation. The inclusion of less reliable judges can introduce noise, undermining the overall reliability of the outcomes. To explore the factors that impact evaluation reliability, we fine-tune an underperforming VLM judge, Video-LLaVA, and observe that improved understanding ability alone is insufficient to make VLM judges more reliable. These findings stress the limitations of collective thought approaches and highlight the need for more advanced methods that can account for the reliability of individual models. Our study promotes the development of more reliable evaluation methods for VLMs. Figure 1: By contrasting reviewing results from one VLM with multi-LLM Agent-Debate, we find that some VLMs are far from being able to provide reliable reviews. More and more video language models (VLMs) have been developed for video understanding.

We present a novel approach to selective model quantization that transcends the limitations of architecture-specific and size-dependent compression methods for Large Language Models (LLMs) using Entropy-Weighted Quantization (EWQ). By analyzing the entropy distribution across transformer blocks, EWQ determines which blocks can be safely quantized without causing significant performance degradation, independent of model architecture or size. Our method outperforms uniform quantization approaches, maintaining Massive Multitask Language Understanding (MMLU) accuracy scores within 0.5% of unquantized models while reducing memory usage by up to 18%. We demonstrate the effectiveness of EWQ across multiple architectures -- from 1.6B to 70B parameters -- and showcase consistent improvements in the quality-compression trade-off regardless of model scale or architectural design. A surprising finding of EWQ is its ability to reduce perplexity compared to unquantized models, suggesting the presence of beneficial regularization through selective precision reduction. This improvement holds across different model families, indicating a fundamental relationship between layer-level entropy and optimal precision requirements. Additionally, we introduce FastEWQ, a rapid method for entropy distribution analysis that eliminates the need for loading model weights. This technique leverages universal characteristics of entropy distribution that persist across various architectures and scales, enabling near-instantaneous quantization decisions while maintaining 80% classification accuracy with full entropy analysis. Our results demonstrate that effective quantization strategies can be developed independently of specific architectural choices or model sizes, opening new possibilities for efficient LLM deployment.

Large language models (LLMs) have demonstrated remarkable capabilities in handling complex dialogue tasks without requiring use case-specific fine-tuning. However, analyzing live dialogues in real-time necessitates low-latency processing systems, making it impractical to deploy models with billions of parameters due to latency constraints. As a result, practitioners often prefer smaller models with millions of parameters, trained on high-quality, human-annotated datasets. Yet, curating such datasets is both time-consuming and costly. Consequently, there is a growing need to combine the scalability of LLM-generated labels with the precision of human annotations, enabling fine-tuned smaller models to achieve both higher speed and accuracy comparable to larger models. In this paper, we introduce a simple yet effective framework to address this challenge. Our approach is specifically designed for per-utterance classification problems, which encompass tasks such as intent detection, dialogue state tracking, and more. To mitigate the impact of labeling errors from LLMs -- the primary source of inaccuracies in student models -- we propose a noise-reduced preference learning loss. Experimental results demonstrate that our method significantly improves accuracy across utterance-level dialogue tasks, including sentiment detection (over $2\%$), dialogue act classification (over $1.5\%$), etc.

Recent advances in large language models have demonstrated remarkable reasoning capabilities through Chain of Thought (CoT) prompting, but often at the cost of excessive verbosity in their intermediate outputs, which increases computational overhead. We introduce Sketch-of-Thought (SoT), a novel prompting framework that combines cognitive-inspired reasoning paradigms with linguistic constraints to minimize token usage while preserving reasoning accuracy. SoT is designed as a flexible framework that can incorporate any custom reasoning paradigms based on cognitive science, and we instantiate it with three such paradigms - Conceptual Chaining, Chunked Symbolism, and Expert Lexicons - each tailored to different reasoning tasks and selected dynamically via a lightweight routing model. Through comprehensive evaluation across 15 reasoning datasets with multiple languages and multimodal scenarios, we demonstrate that SoT achieves token reductions of 76% with negligible accuracy impact. In certain domains like mathematical and multi-hop reasoning, it even improves accuracy while using significantly fewer tokens. Our code is publicly available: https://www.github.com/SimonAytes/SoT.

Document Key Information Extraction (KIE) is a technology that transforms valuable information in document images into structured data, and it has become an essential function in industrial settings. However, current evaluation metrics of this technology do not accurately reflect the critical attributes of its industrial applications. In this paper, we present KIEval, a novel application-centric evaluation metric for Document KIE models. Unlike prior metrics, KIEval assesses Document KIE models not just on the extraction of individual information (entity) but also of the structured information (grouping). Evaluation of structured information provides assessment of Document KIE models that are more reflective of extracting grouped information from documents in industrial settings. Designed with industrial application in mind, we believe that KIEval can become a standard evaluation metric for developing or applying Document KIE models in practice. The code will be publicly available.

As large language models (LLMs) are increasingly deployed as service endpoints in systems, the surge in query volume creates significant scheduling challenges. Existing scheduling frameworks mainly target at latency optimization while neglecting the capability of LLMs to serve different level of queries, which could lead to computational resource waste. This paper addresses this challenge by proposing a capability-cost coordinated scheduling framework, ECCOS, for multi-LLM serving, which explicitly constrains response quality and workload to optimize LLM inference cost. Specifically, it introduces the two-stage scheduling by designing a multi-objective predictor and a constrained optimizer. The predictor estimates both model capabilities and computational costs through training-based and retrieval-based approaches, while the optimizer determines cost-optimal assignments under quality and workload constraints. It also introduces QAServe, a dataset collected for sample-wise response quality and costs by zero-shot prompting different LLMs on knowledge QA and mathematical reasoning. Extensive experiments demonstrate that ECCOS improves success rates by 6.30% while reducing costs by 10.15% compared to existing methods, consuming less than 0.5% of LLM response time. The code is available at: https://github.com/agiresearch/ECCOS.

Code embeddings are essential for semantic code search; however, current approaches often struggle to capture the precise syntactic and contextual nuances inherent in code. Open-source models such as CodeBERT and UniXcoder exhibit limitations in scalability and efficiency, while high-performing proprietary systems impose substantial computational costs. We introduce a parameter-efficient fine-tuning method based on Low-Rank Adaptation (LoRA) to construct task-specific adapters for code retrieval. Our approach reduces the number of trainable parameters to less than two percent of the base model, enabling rapid fine-tuning on extensive code corpora (2 million samples in 25 minutes on two H100 GPUs). Experiments demonstrate an increase of up to 9.1% in Mean Reciprocal Rank (MRR) for Code2Code search, and up to 86.69% for Text2Code search tasks across multiple programming languages. Distinction in task-wise and language-wise adaptation helps explore the sensitivity of code retrieval for syntactical and linguistic variations.