Evaluating Language Model Pluralism through In-the-wild Crowd Discussions
Published in ACL 2026, 2026
Evaluating language model pluralism through in-the-wild crowd discussions.
Publications
WS-GRPO: Weakly-Supervised Group-Relative Policy Optimization
Published in ICML 2026, 2026
Weakly-Supervised Group-Relative Policy Optimization for variational inference and AI-Agentic benchmarks.
WildScore: Benchmarking MLLMs in-the-Wild Symbolic Music Reasoning
Published in EMNLP 2025 - Main Conference, 2025
A benchmark for evaluating vision/audio reasoning in Multimodal Large Language Models (MLLMs) with symbolic music understanding.
MusiCRS: Benchmarking Music-Centric Conversational Recommendation
Published in IEEE ICASSP 2026, 2025
A benchmark for evaluating music-centric conversational recommendation systems with 482 audio-query cases.
SINR-Delay Constrained Node Localization in RIS-Assisted Time-Varying IoT Networks Using ML Frameworks
Published in IEEE TNSM, 2025, 2025
Machine learning frameworks for node localization in RIS-assisted IoT networks with SINR and delay constraints.
Deep learning-based hyperspectral microscopic imaging for cholangiocarcinoma detection and classification
Published in Optics Continuum, 2024
Deep learning approach for detecting and classifying cholangiocarcinoma using hyperspectral microscopic imaging.