James R. Glass

17 papers · 2005–2025 · 6 venues · across top CS/AI venues

Authors are matched by name, so researchers who share a name ("Yang Liu", "Wei Wang") appear as a single profile and their paper counts, venues and achievements are combined. How identity is handled.

Achievements

Jump to papers ↓

+4 more ↓

🌉 Interdisciplinary Bridge · Silver 🗺️ Taxonomy Completionist (38) 🌍 Conference Polyglot · Silver 🐣 Hot Topic Early Bird 🏃 Academic Marathon · Ultra

🌈 Renaissance Researcher (6) ⚡ Prolific Year · Prolific 💎 Century Club · Bronze 🗃️ Keyword Collector (81)

Venues

ICLR (7) EMNLP (4) ACL (3) CVPR (1) ICML (1) NAACL (1)

Top co-authors

Hongyin Luo (9) Helen M. Meng (4) Yung-Sung Chuang (4) Yuan Gong (4) Leonid Karlinsky (4) Xixin Wu (4) Kun Li (4) Tianhua Zhang (4) Alexander H. Liu (3) Hilde Kuehne (2)

Research topics

Artificial Intelligence (14) Core AI (14) Machine Learning (11) Learning Types · Machine Learning (8) Natural Language Processing (7) Deep Learning (6) Resources & Methods (4) Applications (3) Learning Types · Deep Learning (3) Architectures (2) Models (2) Optimization & Theory (2) Computer Vision (1) Knowledge & Reasoning (1) Reinforcement Learning (1)

Keywords

large language model (6) masked autoencoder (2) retrieval-augmented generation (2) contrastive learning (2) question answering (2) multimodal representation (2) reinforcement learning (2) few-shot learning (1) preference optimization (1) feature learning (1) speech recognition (1) self-supervised learning (1) multimodal learning (1) passage retrieval (1) zero-shot learning (1) audio-visual learning (1) knowledge graph question answering (1) direct preference optimization (1) model merging (1) language model evaluation (1)

Papers

CAV-MAE Sync: Improving Contrastive Audio-Visual Mask Autoencoders via Fine-Grained Alignment CVPR 2025 Decoding on Graphs: Faithful and Sound Reasoning on Knowledge Graphs through Generation of Well-Formed Chains ACL 2025 Generate, Discriminate, Evolve: Enhancing Context Faithfulness via Fine-Grained Sentence-Level Self-Evolution ACL 2025 PLAY2PROMPT: Zero-shot Tool Instruction Optimization for LLM Agents via Tool Play ACL 2025 Quantifying Generalization Complexity for Large Language Models ICLR 2025 RAG-Zeval: Enhancing RAG Responses Evaluator through End-to-End Reasoning and Ranking-Based Reinforcement Learning EMNLP 2025 SelfCite: Self-Supervised Alignment for Context Attribution in Large Language Models ICML 2025 Self-MoE: Towards Compositional Large Language Models with Self-Specialized Experts ICLR 2025 THREAD: Thinking Deeper with Recursive Spawning NAACL 2025 UniWav: Towards Unified Pre-training for Speech Representation Learning and Generation ICLR 2025 Adaptive Query Rewriting: Aligning Rewriters through Marginal Probability of Conversational Answers EMNLP 2024 Curiosity-driven Red-teaming for Large Language Models ICLR 2024 DoLa: Decoding by Contrasting Layers Improves Factuality in Large Language Models ICLR 2024 Listen, Think, and Understand ICLR 2024 Lookback Lens: Detecting and Mitigating Contextual Hallucinations in Large Language Models Using Only Attention Maps EMNLP 2024 Contrastive Audio-Visual Masked Autoencoder ICLR 2023 The MIT Spoken Lecture Processing Project EMNLP 2005