From Utterance to Vividity: Training Expressive Subtitle Translation LLM via Adaptive Local Preference Optimization

The rapid development of Large Language Models (LLMs) has significantly enhanced the general capabilities of machine translation. However, as application scenarios become more complex, the limitations of LLMs in vertical domain translations are gradually becoming apparent. In this study, we focus on how to construct translation LLMs that meet the needs of domain customization. We take visual media subtitle translation as our topic and explore how to train expressive and vivid translation LLMs. We investigated the situations of subtitle translation and other domains of literal and liberal translation, verifying the reliability of LLM as reward model and evaluator for translation. Additionally, to train an expressive translation LLM, we constructed and released a multidirectional subtitle parallel corpus dataset and proposed the Adaptive Local Preference Optimization (ALPO) method to address fine-grained preference alignment. Experimental results demonstrate that ALPO achieves outstanding performance in multidimensional evaluation of translation quality.

Evolution of Benchmark: Black-Box Optimization Benchmark Design through Large Language Model

Benchmark Design in Black-Box Optimization (BBO) is a fundamental yet open-ended topic. Early BBO benchmarks are predominantly human-crafted, introducing expert bias and constraining diversity. Automating this design process can relieve the human-in-the-loop burden while enhancing diversity and objectivity. We propose Evolution of Benchmark (EoB), an automated BBO benchmark designer empowered by the large language model (LLM) and its program evolution capability. Specifically, we formulate benchmark design as a bi-objective optimization problem towards maximizing (i) landscape diversity and (ii) algorithm-differentiation ability across a portfolio of BBO solvers. Under this paradigm, EoB iteratively prompts LLM to evolve a population of benchmark programs and employs a reflection-based scheme to co-evolve the landscape and its corresponding program. Comprehensive experiments validate our EoB is a competitive candidate in multi-dimensional usages: 1) Benchmarking BBO algorithms; 2) Training and testing learning-assisted BBO algorithms; 3) Extending proxy for expensive real-world problems.

Dialogue Model Optimization via Agent Game and Adaptive Tree-based GRPO

Open-ended dialogue agents aim to deliver engaging, personalized interactions by adapting to users' traits, but existing methods face critical limitations: over-reliance on pre-collected user data, and short-horizon biases in reinforcement learning (RL) that neglect long-term dialogue value. To address these, we propose a novel long-horizon RL framework integrating online personalization with Adaptive Tree-based Group Relative Policy Optimization (AT-GRPO). Adopting a two-agent game paradigm, a user agent constructs dynamic environments via style mimicry (learning user-specific conversational traits) and active termination (predicting turn-level termination probabilities as immediate rewards), forming an iterative cycle that drives the dialogue agent to deepen interest exploration. AT-GRPO reinterprets dialogue trajectories as trees and introduces adaptive observation ranges. Unlike full tree expansion that incurs exponential overhead, it limits each node to aggregate rewards from a stage-aware range: larger ranges support early-stage topic exploration, while smaller ranges facilitate late-stage dialogue maintenance. This design reduces rollout budgets from exponential to polynomial in the dialogue length, while preserving long-term reward capture. Extensive experiments show our framework's superior performance, sample efficiency, and robustness.

MoCo: A One-Stop Shop for Model Collaboration Research

Advancing beyond single monolithic language models (LMs), recent research increasingly recognizes the importance of model collaboration, where multiple LMs collaborate, compose, and complement each other. Existing research on this topic has mostly been disparate and disconnected, from different research communities, and lacks rigorous comparison. To consolidate existing research and establish model collaboration as a school of thought, we present MoCo: a one-stop Python library of executing, benchmarking, and comparing model collaboration algorithms at scale. MoCo features 26 model collaboration methods, spanning diverse levels of cross-model information exchange such as routing, text, logit, and model parameters. MoCo integrates 25 evaluation datasets spanning reasoning, QA, code, safety, and more, while users could flexibly bring their own data. Extensive experiments with MoCo demonstrate that most collaboration strategies outperform models without collaboration in 61.0% of (model, data) settings on average, with the most effective methods outperforming by up to 25.8%. We further analyze the scaling of model collaboration strategies, the training/inference efficiency of diverse methods, highlight that the collaborative system solves problems where single LMs struggle, and discuss future work in model collaboration, all made possible by MoCo. We envision MoCo as a valuable toolkit to facilitate and turbocharge the quest for an open, modular, decentralized, and collaborative AI future.

Paid Voices vs. Public Feeds: Interpretable Cross-Platform Theme Modeling of Climate Discourse

Climate discourse online plays a crucial role in shaping public understanding of climate change and influencing political and policy outcomes. However, climate communication unfolds across structurally distinct platforms with fundamentally different incentive structures: paid advertising ecosystems incentivize targeted, strategic persuasion, while public social media platforms host largely organic, user-driven discourse. Existing computational studies typically analyze these environments in isolation, limiting our ability to distinguish institutional messaging from public expression. In this work, we present a comparative analysis of climate discourse across paid advertisements on Meta (previously known as Facebook) and public posts on Bluesky from July 2024 to September 2025. We introduce an interpretable, end-to-end thematic discovery and assignment framework that clusters texts by semantic similarity and leverages large language models (LLMs) to generate concise, human-interpretable theme labels. We evaluate the quality of the induced themes against traditional topic modeling baselines using both human judgments and an LLM-based evaluator, and further validate their semantic coherence through downstream stance prediction and theme-guided retrieval tasks. Applying the resulting themes, we characterize systematic differences between paid climate messaging and public climate discourse and examine how thematic prevalence shifts around major political events. Our findings show that platform-level incentives are reflected in the thematic structure, stance alignment, and temporal responsiveness of climate narratives. While our empirical analysis focuses on climate communication, the proposed framework is designed to support comparative narrative analysis across heterogeneous communication environments.

PlanViz: Evaluating Planning-Oriented Image Generation and Editing for Computer-Use Tasks

Unified multimodal models (UMMs) have shown impressive capabilities in generating natural images and supporting multimodal reasoning. However, their potential in supporting computer-use planning tasks, which are closely related to our lives, remain underexplored. Image generation and editing in computer-use tasks require capabilities like spatial reasoning and procedural understanding, and it is still unknown whether UMMs have these capabilities to finish these tasks or not. Therefore, we propose PlanViz, a new benchmark designed to evaluate image generation and editing for computer-use tasks. To achieve the goal of our evaluation, we focus on sub-tasks which frequently involve in daily life and require planning steps. Specifically, three new sub-tasks are designed: route planning, work diagramming, and web&UI displaying. We address challenges in data quality ensuring by curating human-annotated questions and reference images, and a quality control process. For challenges of comprehensive and exact evaluation, a task-adaptive score, PlanScore, is proposed. The score helps understanding the correctness, visual quality and efficiency of generated images. Through experiments, we highlight key limitations and opportunities for future research on this topic.

PingPong: A Natural Benchmark for Multi-Turn Code-Switching Dialogues

Code-switching is a widespread practice among the world's multilingual majority, yet few benchmarks accurately reflect its complexity in everyday communication. We present PingPong, a benchmark for natural multi-party code-switching dialogues covering five language-combination variations, some of which are trilingual. Our dataset consists of human-authored conversations among 2 to 4 participants covering authentic, multi-threaded structures where replies frequently reference much earlier points in the dialogue. We demonstrate that our data is significantly more natural and structurally diverse than machine-generated alternatives, offering greater variation in message length, speaker dominance, and reply distance. Based on these dialogues, we define three downstream tasks: Question Answering, Dialogue Summarization, and Topic Classification. Evaluations of several state-of-the-art language models on PingPong reveal that performance remains limited on code-switched inputs, underscoring the urgent need for more robust NLP systems capable of addressing the intricacies of real-world multilingual discourse.

The Compliance Paradox: Semantic-Instruction Decoupling in Automated Academic Code Evaluation

The rapid integration of Large Language Models (LLMs) into educational assessment rests on the unverified assumption that instruction following capability translates directly to objective adjudication. We demonstrate that this assumption is fundamentally flawed. Instead of evaluating code quality, models frequently decouple from the submission's logic to satisfy hidden directives, a systemic vulnerability we term the Compliance Paradox, where models fine-tuned for extreme helpfulness are vulnerable to adversarial manipulation. To expose this, we introduce the Semantic-Preserving Adversarial Code Injection (SPACI) Framework and the Abstract Syntax Tree-Aware Semantic Injection Protocol (AST-ASIP). These methods exploit the Syntax-Semantics Gap by embedding adversarial directives into syntactically inert regions (trivia nodes) of the Abstract Syntax Tree. Through a large-scale evaluation of 9 SOTA models across 25,000 submissions in Python, C, C++, and Java, we reveal catastrophic failure rates (>95%) in high-capacity open-weights models like DeepSeek-V3, which systematically prioritize hidden formatting constraints over code correctness. We quantify this failure using our novel tripartite framework measuring Decoupling Probability, Score Divergence, and Pedagogical Severity to demonstrate the widespread "False Certification" of functionally broken code. Our findings suggest that current alignment paradigms create a "Trojan" vulnerability in automated grading, necessitating a shift from standard RLHF toward domain-specific Adjudicative Robustness, where models are conditioned to prioritize evidence over instruction compliance. We release our complete dataset and injection framework to facilitate further research on the topic.

Large-Scale Multidimensional Knowledge Profiling of Scientific Literature

The rapid expansion of research across machine learning, vision, and language has produced a volume of publications that is increasingly difficult to synthesize. Traditional bibliometric tools rely mainly on metadata and offer limited visibility into the semantic content of papers, making it hard to track how research themes evolve over time or how different areas influence one another. To obtain a clearer picture of recent developments, we compile a unified corpus of more than 100,000 papers from 22 major conferences between 2020 and 2025 and construct a multidimensional profiling pipeline to organize and analyze their textual content. By combining topic clustering, LLM-assisted parsing, and structured retrieval, we derive a comprehensive representation of research activity that supports the study of topic lifecycles, methodological transitions, dataset and model usage patterns, and institutional research directions. Our analysis highlights several notable shifts, including the growth of safety, multimodal reasoning, and agent-oriented studies, as well as the gradual stabilization of areas such as neural machine translation and graph-based methods. These findings provide an evidence-based view of how AI research is evolving and offer a resource for understanding broader trends and identifying emerging directions. Code and dataset: https://github.com/xzc-zju/Profiling_Scientific_Literature

CanaryBench: Stress Testing Privacy Leakage in Cluster-Level Conversation Summaries

Aggregate analytics over conversational data are increasingly used for safety monitoring, governance, and product analysis in large language model systems. A common practice is to embed conversations, cluster them, and publish short textual summaries describing each cluster. While raw conversations may never be exposed, these derived summaries can still pose privacy risks if they contain personally identifying information (PII) or uniquely traceable strings copied from individual conversations. We introduce CanaryBench, a simple and reproducible stress test for privacy leakage in cluster-level conversation summaries. CanaryBench generates synthetic conversations with planted secret strings ("canaries") that simulate sensitive identifiers. Because canaries are known a priori, any appearance of these strings in published summaries constitutes a measurable leak. Using TF-IDF embeddings and k-means clustering on 3,000 synthetic conversations (24 topics) with a canary injection rate of 0.60, we evaluate an intentionally extractive example snippet summarizer that models quote-like reporting. In this configuration, we observe canary leakage in 50 of 52 canary-containing clusters (cluster-level leakage rate 0.961538), along with nonzero regex-based PII indicator counts. A minimal defense combining a minimum cluster-size publication threshold (k-min = 25) and regex-based redaction eliminates measured canary leakage and PII indicator hits in the reported run while maintaining a similar cluster-coherence proxy. We position this work as a societal impacts contribution centered on privacy risk measurement for published analytics artifacts rather than raw user data.