AdsQA: Towards Advertisement Video Understanding

Large language models (LLMs) have taken a great step towards AGI. Meanwhile, an increasing number of domain-specific problems such as math and programming boost these general-purpose models to continuously evolve via learning deeper expertise. Now is thus the time further to extend the diversity of specialized applications for knowledgeable LLMs, though collecting high quality data with unexpected and informative tasks is challenging. In this paper, we propose to use advertisement (ad) videos as a challenging test-bed to probe the ability of LLMs in perceiving beyond the objective physical content of common visual domain. Our motivation is to take full advantage of the clue-rich and information-dense ad videos' traits, e.g., marketing logic, persuasive strategies, and audience engagement. Our contribution is three-fold: (1) To our knowledge, this is the first attempt to use ad videos with well-designed tasks to evaluate LLMs. We contribute AdsQA, a challenging ad Video QA benchmark derived from 1,544 ad videos with 10,962 clips, totaling 22.7 hours, providing 5 challenging tasks. (2) We propose ReAd-R, a Deepseek-R1 styled RL model that reflects on questions, and generates answers via reward-driven optimization. (3) We benchmark 14 top-tier LLMs on AdsQA, and our \texttt{ReAd-R}~achieves the state-of-the-art outperforming strong competitors equipped with long-chain reasoning capabilities by a clear margin.

ReviewRL: Towards Automated Scientific Review with RL

Peer review is essential for scientific progress but faces growing challenges due to increasing submission volumes and reviewer fatigue. Existing automated review approaches struggle with factual accuracy, rating consistency, and analytical depth, often generating superficial or generic feedback lacking the insights characteristic of high-quality human reviews. We introduce ReviewRL, a reinforcement learning framework for generating comprehensive and factually grounded scientific paper reviews. Our approach combines: (1) an ArXiv-MCP retrieval-augmented context generation pipeline that incorporates relevant scientific literature, (2) supervised fine-tuning that establishes foundational reviewing capabilities, and (3) a reinforcement learning procedure with a composite reward function that jointly enhances review quality and rating accuracy. Experiments on ICLR 2025 papers demonstrate that ReviewRL significantly outperforms existing methods across both rule-based metrics and model-based quality assessments. ReviewRL establishes a foundational framework for RL-driven automatic critique generation in scientific discovery, demonstrating promising potential for future development in this domain. The implementation of ReviewRL will be released at GitHub.

GLM-4.5: Agentic, Reasoning, and Coding (ARC) Foundation Models

We present GLM-4.5, an open-source Mixture-of-Experts (MoE) large language model with 355B total parameters and 32B activated parameters, featuring a hybrid reasoning method that supports both thinking and direct response modes. Through multi-stage training on 23T tokens and comprehensive post-training with expert model iteration and reinforcement learning, GLM-4.5 achieves strong performance across agentic, reasoning, and coding (ARC) tasks, scoring 70.1% on TAU-Bench, 91.0% on AIME 24, and 64.2% on SWE-bench Verified. With much fewer parameters than several competitors, GLM-4.5 ranks 3rd overall among all evaluated models and 2nd on agentic benchmarks. We release both GLM-4.5 (355B parameters) and a compact version, GLM-4.5-Air (106B parameters), to advance research in reasoning and agentic AI systems. Code, models, and more information are available at https://github.com/zai-org/GLM-4.5.

Quantifying Preferences of Vision-Language Models via Value Decomposition in Social Media Contexts

The rapid advancement of Vision-Language Models (VLMs) has expanded multimodal applications, yet evaluations often focus on basic tasks like object recognition, overlooking abstract aspects such as personalities and values. To address this gap, we introduce Value-Spectrum, a visual question-answering benchmark aimed at assessing VLMs based on Schwartz's value dimensions, which capture core values guiding people's beliefs and actions across cultures. We constructed a vectorized database of over 50,000 short videos sourced from TikTok, YouTube Shorts, and Instagram Reels, covering multiple months and a wide array of topics such as family, health, hobbies, society, and technology. We also developed a VLM agent pipeline to automate video browsing and analysis. Benchmarking representative VLMs on Value-Spectrum reveals significant differences in their responses to value-oriented content, with most models exhibiting a preference for hedonistic topics. Beyond identifying natural preferences, we explored the ability of VLM agents to adopt specific personas when explicitly prompted, revealing insights into the models' adaptability in role-playing scenarios. These findings highlight the potential of Value-Spectrum as a comprehensive evaluation set for tracking VLM advancements in value-based tasks and for developing more sophisticated role-playing AI agents.

Toward Less Hidden Cost of Code Completion with Acceptance and Ranking Models

Code completion is widely used by software developers to provide coding suggestions given a partially written code snippet. Apart from the traditional code completion methods, which only support single token completion at minimal positions, recent studies show the ability to provide longer code completion at more flexible positions. However, such frequently triggered and longer completion results reduce the overall precision as they generate more invalid results. Moreover, different studies are mostly incompatible with each other. Thus, it is vital to develop an ensemble framework that can combine results from multiple models to draw merits and offset defects of each model. This paper conducts a coding simulation to collect data from code context and different code completion models and then apply the data in two tasks. First, we introduce an acceptance model which can dynamically control whether to display completion results to the developer. It uses simulation features to predict whether correct results exist in the output of these models. Our best model reduces the percentage of false-positive completion from 55.09% to 17.44%. Second, we design a fusion ranking scheme that can automatically identify the priority of the completion results and reorder the candidates from multiple code completion models. This scheme is flexible in dealing with various models, regardless of the type or the length of their completion results. We integrate this ranking scheme with two frequency models and a GPT-2 styled language model, along with the acceptance model to yield 27.80% and 37.64% increase in TOP1 and TOP5 accuracy, respectively. In addition, we propose a new code completion evaluation metric, Benefit-Cost Ratio(BCR), taking into account the benefit of keystrokes saving and hidden cost of completion list browsing, which is closer to real coder experience scenario.