The DeepSeek models have shown exceptional performance in general scene understanding, question-answering (QA), and text generation tasks, owing to their efficient training paradigm and strong reasoning capabilities. In this study, we investigate the dialogue capabilities of the DeepSeek model in robotic surgery scenarios, focusing on tasks such as Single Phrase QA, Visual QA, and Detailed Description. The Single Phrase QA tasks further include sub-tasks such as surgical instrument recognition, action understanding, and spatial position analysis. We conduct extensive evaluations using publicly available datasets, including EndoVis18 and CholecT50, along with their corresponding dialogue data. Our empirical study shows that, compared to existing general-purpose multimodal large language models, DeepSeek-VL2 performs better on complex understanding tasks in surgical scenes. Additionally, although DeepSeek-V3 is purely a language model, we find that when image tokens are directly inputted, the model demonstrates better performance on single-sentence QA tasks. However, overall, the DeepSeek models still fall short of meeting the clinical requirements for understanding surgical scenes. Under general prompts, DeepSeek models lack the ability to effectively analyze global surgical concepts and fail to provide detailed insights into surgical scenarios. Based on our observations, we argue that the DeepSeek models are not ready for vision-language tasks in surgical contexts without fine-tuning on surgery-specific datasets.

This means software developers are going to become more important to how the world builds and maintains software. Yes, there are many ways their practices will evolve thanks to AI coding assistance, but in a world of proliferating machine-generated code, developer judgment and experience will be vital. Research done by GitClear earlier this year indicates that with AI coding assistants (like GitHub Copilot) going mainstream, code churn -- which GitClear defines as "changes that were either incomplete or erroneous when the author initially wrote, committed, and pushed them to the company's git repo" -- has significantly increased. GitClear also found there was a marked decrease in the number of lines of code that have been moved, a signal for refactored code (essentially the care and feeding to make it more effective). In other words, from the time coding assistants were introduced there's been a pronounced increase in lines of code without a commensurate increase in lines deleted, updated, or replaced.

Executives at artificial intelligence companies may like to tell us that AGI is almost here, but the latest models still need some additional tutoring to help them be as clever as they can. Scale AI, a company that's played a key role in helping frontier AI firms build advanced models, has developed a platform that can automatically test a model across thousands of benchmarks and tasks, pinpoint weaknesses, and flag additional training data that ought to help enhance their skills. Scale, of course, will supply the data required. Scale rose to prominence providing human labor for training and testing advanced AI models. Large language models (LLMs) are trained on oodles of text scraped from books, the web, and other sources.

Rami Sinno is crouched beside a filing cabinet, wrestling a beach-ball sized disc out of a box, when a dull thump echoes around his laboratory. "I just dropped tens of thousands of dollars' worth of material," he says with a laugh. Straightening up, Sinno reveals the goods: a golden silicon wafer, which glitters in the fluorescent light of the lab. This circular platter is divided into some 100 rectangular tiles, each of which contains billions of microscopic electrical switches. These are the brains of Amazon's most advanced chip yet: the Trainium 2, announced in December.

If asked to come up with a quintessentially "human" work of art, one could do worse than to name a film by Studio Ghibli. The Japanese animation studio, founded by the legendary eighty-four-year-old director Hayao Miyazaki, is known for its hand-drawn imagery, lushly organic color palettes, epic narratives, and evocation of both the emotional ambiguities of childhood and the twisting path to becoming an adult. We American millennials were blessed to have the films translated and distributed in English just as we were growing up, and so movies including "My Neighbor Totoro," "Princess Mononoke," and "Spirited Away" are nigh-universally recognizable touchstones of our youth. Any Ghibli imagery is primed to make us feel a combination of pleasurable nostalgia and mournful shivers, evoking the doomed forest creatures, greedy bathhouse ghosts, and missed connections featured in Miyazaki's cinematic story lines. Unfortunately, that sense of poignancy quickly erodes when you are bombarded with thousands of Ghibli-esque copycat images, as we all were online last week, thanks to OpenAI's latest version of its ChatGPT tool.

--Audio-Visual Question Answering (A VQA) is a challenging multimodal reasoning task requiring intelligent systems to answer natural language queries based on paired audio-video inputs accurately. However, existing A VQA approaches often suffer from overfitting to dataset biases, leading to poor robustness. T o address these challenges, we first introduce a novel dataset, FortisA VQA, constructed in two stages: (1) rephrasing questions in the test split of the public MUSIC-A VQA dataset and (2) introducing distribution shifts across questions. The first stage expands the test space with greater diversity, while the second enables a refined robustness evaluation across rare, frequent, and overall question distributions. Second, we introduce a robust Multimodal Audio-Visual Epistemic Network (MA VEN) that leverages a multifaceted cycle collaborative debiasing strategy to mitigate bias learning. Experimental results demonstrate that our architecture achieves state-of-the-art performance on FortisA VQA, with a notable improvement of 7.81%. Additionally, our evaluation reveals the limited robustness of existing multimodal QA methods. We also verify the plug-and-play capability of our strategy by integrating it with various baseline models across both datasets. UMANS possess the extraordinary capacity to seam-lessly integrate auditory and visual cues, effectively establishing a cohesive relationship between visual and auditory stimuli [1-3]. Jie Ma, Pinghui Wang, Jing Tao and Zhou Su are with the Ministry of Education of Key Laboratory for Intelligent Networks and Network Security, School of Cyber Science and Engineering, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China. Zhitao Gao and Jun Liu are with the Shannxi Provincial Key Laboratory of Big Data Knowledge Engineering, School of Computer Science and Technology, Xi'an Jiaotong University, Xi'an, Shaanxi 710049, China. Qi Chai is with the Information Hub, Hong Kong University of Science and Technology (Guangzhou), Guangzhou, Guangdong, 510000, China. The question in current A VQA datasets is generated by a limited set of predefined templates, which may not be in line with the real-world scenario. Our findings indicate that existing methods such as STG [6] are not robust, which may be attributed to excessive bias learning, such as memorizing statistical regularities between critical question words and answers. It requires the system to learn high-order interaction representations of the concepts encompassed with audio, video, and language modalities. As is known to us [8-10], the high-level reasoning ability of the system mainly relies on large-scale data that does not contain harmful biases or statistical regularities. However, completely avoiding the negative bias in datasets seems challenging [11] due to the inherent skewness in real-world data distributions.

When using LLMs to address Non-Functional Requirements (NFRs), developers may behave differently (e.g., expressing the same NFR in different words). Robust LLMs should output consistent results across these variations; however, this aspect remains underexplored. We propose RobuNFR for evaluating the robustness of LLMs in NFR-aware code generation across four NFR dimensions: design, readability, reliability, and performance, using three methodologies: prompt variation, regression testing, and diverse workflows. Our experiments show that RobuNFR reveals robustness issues in the tested LLMs when considering NFRs in code generation. Specifically, under prompt variation, including NFRs leads to a decrease in Pass@1 by up to 39 percent and an increase in the standard deviation from 0.48 to 2.48 compared to the baseline without NFRs (i.e., Function-Only). While incorporating NFRs generally improves overall NFR metrics, it also results in higher prompt sensitivity. In regression settings, some LLMs exhibit differences across versions, with improvements in one aspect (e.g., reduced code smells) often accompanied by regressions in another (e.g., decreased correctness), revealing inconsistencies that challenge their robustness. When varying workflows, the tested LLMs show significantly different NFR-aware code generation capabilities between two workflows: (1) integrating NFRs and functional requirements into the initial prompt and (2) enhancing Function-Only-generated code with the same NFR.

Soft prompts have been popularized as a cheap and easy way to improve task-specific LLM performance beyond few-shot prompts. Despite their origin as an automated prompting method, however, soft prompts and other trainable prompts remain a black-box method with no immediately interpretable connections to prompting. We create a novel theoretical framework for evaluating the interpretability of trainable prompts based on two desiderata: faithfulness and scrutability. We find that existing methods do not naturally satisfy our proposed interpretability criterion. Instead, our framework inspires a new direction of trainable prompting methods that explicitly optimizes for interpretability. To this end, we formulate and test new interpretability-oriented objective functions for two state-of-the-art prompt tuners: Hard Prompts Made Easy (PEZ) and RLPrompt. Our experiments with GPT-2 demonstrate a fundamental trade-off between interpretability and the task-performance of the trainable prompt, explicating the hardness of the soft prompt interpretability problem and revealing odd behavior that arises when one optimizes for an interpretability proxy.

In this paper, we propose a novel factored agent architecture designed to overcome the limitations of traditional single-agent systems in agentic AI. Our approach decomposes the agent into two specialized components: (1) a large language model (LLM) that serves as a high level planner and in-context learner, which may use dynamically available information in user prompts, (2) a smaller language model which acts as a memorizer of tool format and output. This decoupling addresses prevalent issues in monolithic designs, including malformed, missing, and hallucinated API fields, as well as suboptimal planning in dynamic environments. Empirical evaluations demonstrate that our factored architecture significantly improves planning accuracy and error resilience, while elucidating the inherent trade-off between in-context learning and static memorization. These findings suggest that a factored approach is a promising pathway for developing more robust and adaptable agentic AI systems.

The detection of telecom fraud faces significant challenges due to the lack of high-quality multimodal training data that integrates audio signals with reasoning-oriented textual analysis. To address this gap, we present TeleAntiFraud-28k, the first open-source audio-text slow-thinking dataset specifically designed for automated telecom fraud analysis. Our dataset is constructed through three strategies: (1) Privacy-preserved text-truth sample generation using automatically speech recognition (ASR)-transcribed call recordings (with anonymized original audio), ensuring real-world consistency through text-to-speech (TTS) model regeneration; (2) Semantic enhancement via large language model (LLM)-based self-instruction sampling on authentic ASR outputs to expand scenario coverage; (3) Multi-agent adversarial synthesis that simulates emerging fraud tactics through predefined communication scenarios and fraud typologies. The generated dataset contains 28,511 rigorously processed speech-text pairs, complete with detailed annotations for fraud reasoning. The dataset is divided into three tasks: scenario classification, fraud detection, fraud type classification. Furthermore, we construct TeleAntiFraud-Bench, a standardized evaluation benchmark comprising proportionally sampled instances from the dataset, to facilitate systematic testing of model performance on telecom fraud detection tasks. We also contribute a production-optimized supervised fine-tuning (SFT) model trained on hybrid real/synthetic data, while open-sourcing the data processing framework to enable community-driven dataset expansion. This work establishes a foundational framework for multimodal anti-fraud research while addressing critical challenges in data privacy and scenario diversity. The project will be released at https://github.com/JimmyMa99/TeleAntiFraud.