- Vevo2: A Unified and Controllable Framework for Speech and Singing Voice Generation
Xueyao Zhang, Junan Zhang, Yuancheng Wang, Chaoren Wang, Yuanzhe Chen · Aug 22, 2025 · Citations: 0
Controllable human voice generation, particularly for expressive domains like singing, remains a significant challenge.
- Classification errors distort findings in automated speech processing: examples and solutions from child-development research
Lucas Gautheron, Evan Kidd, Anton Malko, Marvin Lavechin, Alejandrina Cristia · Aug 21, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- HebID: Detecting Social Identities in Hebrew-language Political Text
Guy Mor-Lan, Naama Rivlin-Angert, Yael R. Kaplan, Tamir Sheafer, Shaul R. Shenhav · Aug 21, 2025 · Citations: 0
We benchmark multilabel and single-label encoders alongside 2B-9B-parameter generative LLMs, finding that Hebrew-tuned LLMs provide the best results (macro-F_1 = 0.74).
- AmbiSQL: Interactive Ambiguity Detection and Resolution for Text-to-SQL
Zhongjun Ding, Yin Lin, Tianjing Zeng, Rong Zhu, Bolin Ding · Aug 21, 2025 · Citations: 0
Demonstrations
We provide 40 ambiguous queries collected from two real-world benchmarks that SIGMOD'26 attendees can use to explore how disambiguation improves SQL generation quality.
- Mapping the Course for Prompt-based Structured Prediction
Matt Pauk, Maria Leonor Pacheco · Aug 20, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Quantization Meets dLLMs: A Systematic Study of Post-training Quantization for Diffusion LLMs
Haokun Lin, Haobo Xu, Yichen Wu, Ziyu Guo, Renrui Zhang · Aug 20, 2025 · Citations: 0
More importantly, we implement state-of-the-art PTQ methods and conduct a comprehensive evaluation across multiple task types and model variants.
- Can synthetic data reproduce real-world findings in epidemiology? A replication study using adversarial random forests
Jan Kapar, Kathrin Günther, Lori Ann Vallis, Klaus Berger, Nadine Binder · Aug 19, 2025 · Citations: 0
Furthermore, common evaluation strategies for synthetic data often fail to directly reflect statistical utility and measure privacy risks sufficiently.
- Tokens with Meaning: A Hybrid Tokenization Approach for Turkish
M. Ali Bayram, Ali Arda Fincan, Ahmet Semih Gümüş, Sercan Karakaş, Banu Diri · Aug 19, 2025 · Citations: 0
We further validate practical utility with downstream sentence embedding benchmarks under a strict random initialization control to isolate tokenizer inductive bias.
- Embodied-R1: Reinforced Embodied Reasoning for General Robotic Manipulation
Yifu Yuan, Haiqin Cui, Yaoting Huang, Yibin Chen, Fei Ni · Aug 19, 2025 · Citations: 0
- Chunks as Arms: Multi-Armed Bandit-Guided Sampling for Long-Context LLM Preference Optimization
Shaohua Duan, Pengcheng Huang, Xinze Li, Zhenghao Liu, Xiaoyuan Yi · Aug 19, 2025 · Citations: 0
Pairwise Preference
To address these challenges, we propose LongMab, a novel framework that leverages a Multi-Armed Bandit (MAB) rollout strategy to identify the most informative chunks from the given long context for sampling high-quality and diverse…
- The Collaboration Paradox: Why Generative AI Requires Both Strategic Intelligence and Operational Stability in Supply Chain Management
Soumyadeep Dhar · Aug 19, 2025 · Citations: 0
- Depth-Breadth Synergy in RLVR: Unlocking LLM Reasoning Gains with Adaptive Exploration
Zhicheng Yang, Zhijiang Guo, Yinya Huang, Yongxin Wang, Dongchun Xie · Aug 19, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- Interactive Query Answering on Knowledge Graphs with Soft Entity Constraints
Daniel Daza, Alberto Bernardi, Luca Costabello, Christophe Gueret, Masoud Mansoury · Aug 19, 2025 · Citations: 0
Pairwise Preference
In practice, many real-world queries involve constraints that are inherently vague or context-dependent, such as preferences for attributes or related categories.
- Breaking the SFT Plateau: Multimodal Structured Reinforcement Learning for Chart-to-Code Generation
Lei Chen, Xuanle Zhao, Zhixiong Zeng, Jing Huang, Liming Zheng · Aug 19, 2025 · Citations: 0
Experimental results demonstrate that MSRL substantially breaks the SFT plateau, improving high-level metrics by 6.2% and 9.9% on ChartMimic and ReachQA benchmarks, respectively.
- MATA: Mindful Assessment of the Telugu Abilities of Large Language Models
Chalamalasetti Kranti, Sowmya Vajjala · Aug 19, 2025 · Citations: 0
In this paper, we introduce MATA, a novel evaluation dataset to assess the ability of Large Language Models (LLMs) in Telugu language, comprising 729 carefully curated multiple-choice and open-ended questions that span diverse linguistic…
- TASER: Table Agents for Schema-guided Extraction and Recommendation
Nicole Cho, Kirsty Fielding, William Watson, Sumitra Ganesh, Manuela Veloso · Aug 18, 2025 · Citations: 0
Critique Edit
To address this, we present TASER (Table Agents for Schema-guided Extraction and Recommendation), a continuously learning, agentic table extraction system that converts highly unstructured, multi-page, heterogeneous tables into normalized,…
- SNAP-UQ: Self-supervised Next-Activation Prediction for Single-Pass Uncertainty in TinyML
Ismail Lamaakal, Chaymae Yahyati, Khalid El Makkaoui, Ibrahim Ouahbi, Yassine Maleh · Aug 18, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- The Yokai Learning Environment: Tracking Beliefs Over Space and Time
Constantin Ruhdorfer, Matteo Bortoletto, Johannes Forkel, Jakob Foerster, Andreas Bulling · Aug 17, 2025 · Citations: 0
- TaoSR1: The Thinking Model for E-commerce Relevance Search
Chenhe Dong, Shaowei Yao, Pengkun Jiao, Jianhui Yang, Yiming Jin · Aug 17, 2025 · Citations: 0
Pairwise Preference
Our framework, TaoSR1, involves three stages: (1) Supervised Fine-Tuning (SFT) with CoT to instill reasoning; (2) Offline sampling with a pass@N strategy and Direct Preference Optimization (DPO) to improve generation quality; and (3)…
- SEA-BED: How Do Embedding Models Represent Southeast Asian Languages?
Wuttikorn Ponwitayarat, Peerat Limkonchotiwat, Raymond Ng, Jann Railey Montalan, Thura Aung · Aug 17, 2025 · Citations: 0
We introduce SEA-BED, a large-scale benchmark covering 10 Southeast Asian (SEA) languages and diverse embedding tasks, designed to systematically examine how embedding performance varies across tasks, languages, and language-task…
- CORE: Measuring Multi-Agent LLM Interaction Quality under Game-Theoretic Pressures
Punya Syon Pandey, Yongjin Yang, Jiarui Liu, Zhijing Jin · Aug 16, 2025 · Citations: 0
Pairwise Preference Multi Agent
Game-theoretic interactions between agents with Large Language Models (LLMs) have revealed many emergent capabilities, yet the linguistic diversity of these interactions has not been sufficiently quantified.
- Singing Syllabi with Virtual Avatars: Enhancing Student Engagement Through AI-Generated Music and Digital Embodiment
Xinxing Wu · Aug 16, 2025 · Citations: 0
- SafeSieve: From Heuristics to Experience in Progressive Pruning for LLM-based Multi-Agent Communication
Ruijia Zhang, Xinyan Zhao, Ruixiang Wang, Sigen Chen, Guibin Zhang · Aug 15, 2025 · Citations: 0
- CRAFT-GUI: Curriculum-Reinforced Agent For GUI Tasks
Songqin Nong, Xiaoxuan Tang, Jingxuan Xu, Sheng Zhou, Jianfeng Chen · Aug 15, 2025 · Citations: 0
- Role-Augmented Intent-Driven Generative Search Engine Optimization
Xiaolu Chen, Haojie Wu, Jie Bao, Zhen Chen, Yong Liao · Aug 15, 2025 · Citations: 0
Rubric Rating Web Browsing
To better evaluate the method under realistic settings, we address the benchmarking limitations of prior work by: (1) extending the GEO dataset with diversified query variations reflecting real-world search scenarios and (2) introducing…
- Agentic Design Review System
Sayan Nag, K J Joseph, Koustava Goswami, Vlad I Morariu, Balaji Vasan Srinivasan · Aug 14, 2025 · Citations: 0
- GenOM: Ontology Matching with Description Generation and Large Language Model
Yiping Song, Jiaoyan Chen, Renate A. Schmidt · Aug 14, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- The GPT-4o Shock Emotional Attachment to AI Models and Its Impact on Regulatory Acceptance: A Cross-Cultural Analysis of the Immediate Transition from GPT-4o to GPT-5
Hiroki Naito · Aug 14, 2025 · Citations: 0
- UniPrompt-CL: Sustainable Continual Learning in Medical AI with Unified Prompt Pools
Gyutae Oh, Jitae Shin · Aug 14, 2025 · Citations: 0
- CATNet: A geometric deep learning approach for CAT bond spread prediction in the primary market
Dixon Domfeh, Saeid Safarveisi · Aug 13, 2025 · Citations: 0
- UbiQTree: Uncertainty Quantification in XAI with Tree Ensembles
Akshat Dubey, Aleksandar Anžel, Bahar İlgen, Georges Hattab · Aug 13, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- From Context to Intent: Reasoning-Guided Function-Level Code Completion
Yanzhou Li, Tianlin Li, Yiran Zhang, Shangqing Liu, Aishan Liu · Aug 13, 2025 · Citations: 0
- PEER: Unified Process-Outcome Reinforcement Learning for Structured Empathetic Reasoning
Yunxiao Wang, Meng Liu, Kaiyu Jiang, Bin Wen, Fan Yang · Aug 13, 2025 · Citations: 0
Pairwise Preference
Supporters need to understand the seeker's situation and emotions, adopt an appropriate strategy, and respond in a natural, human-like manner.
- IAG: Input-aware Backdoor Attack on VLM-based Visual Grounding
Junxian Li, Beining Xu, Simin Chen, Jiatong Li, Jingdi Lei · Aug 13, 2025 · Citations: 0
Extensive experiments on multiple VLMs (e.g., LLaVA, InternVL, Ferret) and benchmarks (RefCOCO, RefCOCO+, RefCOCOg, Flickr30k Entities, and ShowUI) demonstrate that IAG achieves the best ASRs compared with other baselines on almost all…
- Shadow in the Cache: Unveiling and Mitigating Privacy Risks of KV-cache in LLM Inference
Zhifan Luo, Shuo Shao, Su Zhang, Lijing Zhou, Yuke Hu · Aug 13, 2025 · Citations: 0
Abstract shows limited direct human-feedback or evaluation-protocol detail; use as adjacent methodological context.
- SegDAC: Visual Generalization in Reinforcement Learning via Dynamic Object Tokens
Alexandre Brown, Glen Berseth · Aug 12, 2025 · Citations: 0
- Link Prediction for Event Logs in the Process Industry
Anastasia Zhukova, Thomas Walton, Christian E. Lobmüller, Bela Gipp · Aug 12, 2025 · Citations: 0
Knowledge management in the process industry uses RAG-based applications to optimize operations, ensure safety, and facilitate continuous improvement by effectively leveraging operational data and past insights.
- Can LLMs Detect Their Confabulations? Estimating Reliability in Uncertainty-Aware Language Models
Tianyi Zhou, Johanne Medina, Sanjay Chawla · Aug 11, 2025 · Citations: 0
Large Language Models (LLMs) are prone to generating fluent but incorrect content, known as confabulation, which poses increasing risks in multi-turn or agentic applications where outputs may be reused as context.
- DIVER: A Multi-Stage Approach for Reasoning-intensive Information Retrieval
Duolin Sun, Meixiu Long, Dan Yang, Junjie Wang, Yecheng Luo · Aug 11, 2025 · Citations: 0
- 1-2-3 Check: Enhancing Contextual Privacy in LLM via Multi-Agent Reasoning
Wenkai Li, Liwen Sun, Zhenxiang Guan, Xuhui Zhou, Maarten Sap · Aug 11, 2025 · Citations: 0
Multi Agent
We introduce a multi-agent framework that decomposes privacy reasoning into specialized subtasks (extraction, classification), reducing the information load on any single agent while enabling iterative validation and more reliable adherence
- Klear-Reasoner: Advancing Reasoning Capability via Gradient-Preserving Clipping Policy Optimization
Zhenpeng Su, Leiyu Pan, Xue Bai, Dening Liu, Guanting Dong · Aug 11, 2025 · Citations: 0
We present Klear-Reasoner, a model with long reasoning capabilities that demonstrates careful deliberation during problem solving, achieving outstanding performance across multiple benchmarks.