KC
Kai-Wei Chang
cs.CLcs.AIcs.LGcs.CVstat.MLcs.CYeess.AScs.MMcs.SDcs.RO
On Valency
published · living versionsW_x8yufh22·v1 · currentpublished
MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant
with Yi-Jen Shih, Shih-Yun Shan Kuan, Guan-Ting Lin, Siddhant Arora +5
1 version
Preprints & journals
269 papers in the corpus · 2014–2026Tev: Scaling Long-Horizon Agentic Environments with Dense Progress Rewards2610.18868v1 · Wenbo Hu, Shraman Pramanick, Krishna Kumar Singh et al.2026 · 0 citationsarXiv
D2: High-Capability Full-Duplex Spoken Language Models from Half-Duplex Backbones2610.17124v1 · Cheng-Kuang Chang, Alexander H. Liu, Brian Kingsbury et al.2026 · 0 citationsarXiv
MiniCorp: The Last Mile to an AI Agent Corporation2610.05912v2 · Jingying Zeng, Zhenwei Dai, Jinning Li et al.2026 · 0 citationsarXiv
Overwhelmed by Choice: Studying LLM Decision Making at Scale2609.32809v1 · Yu-Chi Lin, Aryan Seth, Anshul Aravind et al.2026 · 0 citationsarXiv
MP-Bench: Evaluating Voice Agents as a Multiparty Conversation Participant2609.13076v1 · Yi-Jen Shih, Shih-Yun Shan Kuan, Guan-Ting Lin et al.2026 · 0 citationsarXivon Valency
AudioICL-Bench: A Benchmark for Large Audio Language Model In-Context Learning2609.11252v1 · Jia-Hung Chen, Yi-Cheng Lin, Kai-Wei Chang et al.2026 · 0 citationsarXiv
Codebook Agent: Amortized Topology Design for LLM Multi-Agent Systems2609.02264v1 · Jinxi Yu, Yubei Li, Eric Hanchen Jiang et al.2026 · 0 citationsarXiv
Unsupervised Speech Recognition at the Syllable Level2608.22907v1 · Liming Wang, Kai-Wei Chang, Kunio Kashino et al.2026 · 0 citationsarXiv
From Interpretability to Control: Insights from Six Years of the TrustNLP Workshop2608.11171v1 · Rahul Gupta, Abhinav Mohanty, Anaelia Ovalle et al.2026 · 0 citationsarXiv
Memory as a Controlled Process: Learned Adaptive Memory Management for LLM Agents2607.13591v3 · Eric Hanchen Jiang, Zhi Zhang, Yuchen Wu et al.2026 · 0 citationsarXiv
Overcoming State Inertia in Full-Duplex Spoken Language Models via Activation Steering2606.11386v1 · Cheng-Kuang Chang, Kai-Wei Chang, Alexander H. Liu et al.2026 · 0 citationsarXiv
RRP-Voice: A Longitudinal Dataset and Benchmark for Recurrent Respiratory Papillomatosis Detection2606.01639v1 · Wenze Ren, Ke-Han Lu, Kai-Wei Chang et al.2026 · 0 citationsarXiv
CustomerSim: Benchmarking and Aligning Multimodal Language Models as Retail User Simulators2605.08334v2 · Yada Pruksachatkun, Yixin Wan, Xingrun Chen et al.2026 · 0 citationsarXiv
Emergent Strategic Reasoning Risks in AI: A Taxonomy-Driven Evaluation Framework2604.22119v2 · Tharindu Kumarage, Lisa Bauer, Yao Ma et al.2026 · 0 citationsarXiv
Multimodal Integration of Ambulatory ECG and Clinical Features for Sudden Cardiac Death and Pump Failure Death Prediction★.42078341 · Swee, Steven, Adam, Irsyad, Zheng, Erika Yilin et al.2026 · 0 citationsmedRxiv : the preprint server for health sciences. 2026
IYKYK (But AI Doesn't): Automated Content Moderation Does Not Capture Communities' Heterogeneous Attitudes Towards Reclaimed Language2604.16654v2 · Christina Chance, Rebecca Pattichis, Arjun Subramonian et al.2026 · 0 citationsarXiv
TaigiSpeech: A Low-Resource Real-World Speech Intent Dataset and Preliminary Results with Scalable Data Mining In-the-Wild2603.21478v2 · Kai-Wei Chang, Yi-Cheng Lin, Huang-Cheng Chou et al.2026 · 0 citationsarXiv
TiCo: Time-Controllable Spoken Dialogue Model2603.22267v2 · Kai-Wei Chang, Wei-Chih Chen, En-Pei Hu et al.2026 · 0 citationsarXiv
MotionEdit: Benchmarking and Learning Motion-Centric Image Editing2512.10284v2 · Yixin Wan, Lei Ke, Wenhao Yu et al.2025 · 0 citationsarXiv
HoneyBee: Data Recipes for Vision-Language Reasoners2510.12225v2 · Hritik Bansal, Devendra Singh Sachan, Kai-Wei Chang et al.2025 · 0 citationsarXiv
Towards Unsupervised Speech Recognition at the Syllable-Level2510.03639v1 · Liming Wang, Junrui Ni, Kai-Wei Chang et al.2025 · 0 citationsarXiv
FrameMind: Frame-Interleaved Video Reasoning via Reinforcement Learning2509.24008v3 · Haonan Ge, Yiwei Wang, Kai-Wei Chang et al.2025 · 0 citationsarXiv
InsideOut: Measuring and Mitigating Insider-Outsider Bias in Interview Script Generation2509.21080v2 · Yixin Wan, Xingrun Chen, Kai-Wei Chang2025 · 0 citationsarXiv
Exploring Patients' Perceptions of an Advance Care Planning Intervention in the Emergency Department: A Qualitative Study.40729413 · Shiozawa, Youkie, Morton, Saaya, Shirai, Nanako et al.2025 · 0 citationsAcademic emergency medicine : official journal of the Society for Academic Emergency Medicine. 2025;32(10):1076-1083
DiCoRe: Enhancing Zero-shot Event Detection via Divergent-Convergent LLM Reasoning2506.05128v2 · Tanmay Parekh, Kartik Mehta, Ninareh Mehrabi et al.2025 · 2 citationsarXiv
3DLLM-Mem: Long-Term Spatial-Temporal Memory for Embodied 3D Large Language Model2505.22657v2 · Wenbo Hu, Yining Hong, Yanjun Wang et al.2025 · 3 citationsarXiv
PARTONOMY: Large Multimodal Models with Part-Level Visual Understanding2505.20759v3 · Ansel Blume, Jeonghwan Kim, Hyeonjeong Ha et al.2025 · 0 citationsarXiv
Towards Safety Reasoning in LLMs: AI-agentic Deliberation for Policy-embedded CoT Data Creation2505.21784v1 · Tharindu Kumarage, Ninareh Mehrabi, Anil Ramakrishna et al.2025 · 0 citationsarXiv
LaViDa: A Large Diffusion Language Model for Multimodal Understanding2505.16839v4 · Shufan Li, Konstantinos Kallidromitis, Hritik Bansal et al.2025 · 8 citationsarXiv
Learning to Rank Chain-of-Thought: Using a Small Model2505.14999v3 · Eric Hanchen Jiang, Haozheng Luo, Shengyuan Pang et al.2025 · 0 citationsarXiv
Agree to Disagree? A Meta-Evaluation of LLM Misgendering2504.17075v2 · Arjun Subramonian, Vagrant Gautam, Preethi Seshadri et al.2025 · 0 citationsarXiv
SemEval-2025 Task 4: Unlearning sensitive content from Large Language Models2504.02883v1 · Anil Ramakrishna, Yixin Wan, Xiaomeng Jin et al.2025 · 0 citationsarXiv
When To Solve, When To Verify: Compute-Optimal Problem Solving and Generative Verification for LLM Reasoning2504.01005v2 · Nishad Singhi, Hritik Bansal, Arian Hosseini et al.2025 · 0 citationsarXiv
OpenVLThinker: Complex Vision-Language Reasoning via Iterative SFT-RL Cycles2503.17352v3 · Yihe Deng, Hritik Bansal, Fan Yin et al.2025 · 18 citationsarXiv
The Amazon Nova Family of Models: Technical Report and Model Card2506.12103v1 · Amazon AGI, Aaron Langford, Aayush Shah et al.2025 · 2 citationsarXiv
Magnet: Multi-turn Tool-use Data Synthesis and Distillation via Graph Translation2503.07826v1 · Fan Yin, Zifeng Wang, I-Hung Hsu et al.2025 · 2 citationsarXiv
Towards a holistic framework for multimodal LLM in 3D brain CT radiology report generation.40050277 · Li, Cheng-Yi, Chang, Kao-Jung, Yang, Cheng-Fu et al.2025 · 73 citationsNature communications. 2025;16(1):2258
SYNTHIA: Novel Concept Design with Affordance Composition2502.17793v4 · Hyeonjeong Ha, Xiaomeng Jin, Jeonghwan Kim et al.2025 · 0 citationsarXiv
SNaRe: Domain-aware Data Generation for Low-Resource Event Detection2502.17394v3 · Tanmay Parekh, Yuxuan Dong, Lucas Bandarkar et al.2025 · 1 citationarXiv
METAL: A Multi-Agent Framework for Chart Generation with Test-Time Scaling2502.17651v4 · Bingxuan Li, Yiwei Wang, Jiuxiang Gu et al.2025 · 3 citationsarXiv
LUME: LLM Unlearning with Multitask Evaluations2502.15097v3 · Anil Ramakrishna, Yixin Wan, Xiaomeng Jin et al.2025 · 1 citationarXiv
K-Edit: Language Model Editing with Contextual Knowledge Awareness2502.10626v2 · Elan Markowitz, Anil Ramakrishna, Ninareh Mehrabi et al.2025 · 0 citationsarXiv
QLASS: Boosting Language Agent Inference via Q-Guided Stepwise Search2502.02584v1 · Zongyu Lin, Yao Tang, Xingcheng Yao et al.2025 · 0 citationsarXiv
SafeWorld: Geo-Diverse Safety Alignment2412.06483v1 · Da Yin, Haoyi Qiu, Kung-Hsiang Huang et al.2024 · 1 citationarXiv
DRS: Deep Question Reformulation With Structured Output2411.17993v6 · Zhecheng Li, Yiwei Wang, Bryan Hooi et al.2024 · 0 citationsarXiv
Exploring Visual Vulnerabilities via Multi-Loss Adversarial Search for Jailbreaking Vision-Language Models2411.18000v2 · Shuyang Hao, Bryan Hooi, Jun Liu et al.2024 · 4 citationsarXiv
Verbalized Representation Learning for Interpretable Few-Shot Generalization2411.18651v3 · Cheng-Fu Yang, Da Yin, Wenbo Hu et al.2024 · 1 citationarXiv
The Root Shapes the Fruit: On the Persistence of Gender-Exclusive Harms in Aligned Language Models2411.03700v2 · Anaelia Ovalle, Krunoslav Lehman Pavasovic, Louis Martin et al.2024 · 8 citationsarXiv
SlowFast-VGen: Slow-Fast Learning for Action-Driven Long Video Generation2410.23277v2 · Yining Hong, Beide Liu, Maxine Wu et al.2024 · 0 citationsarXiv
Unlearning as multi-task optimization: A normalized gradient difference approach with an adaptive learning rate2410.22086v3 · Zhiqi Bu, Xiaomeng Jin, Bhanukiran Vinzamuri et al.2024 · 0 citationsarXiv
Career total: 379 works. 269 are in this corpus.Showing the 50 most recent.
Profile built from the corpus for this byline.
Author records are still filling in while the Hub is in alpha. If this is your page, you'll be able to claim it soon. Spot a mistake? Tell us.