conftrace_
← Authors

Sheng Shen

40 papers · 2017–2026 · 12 conferences · across top CS/AI conferences

Achievements

Jump to papers ↓
+15 more ↓ 🧭 Keyword Pioneer 🌍 Conference Polyglot (12) πŸ—ΊοΈ Taxonomy Completionist (11) πŸŒ‰ Interdisciplinary Bridge πŸƒ Academic Marathon (8)
πŸƒ Academic Marathon (8) 🐝 Cross-Pollinator (8) 🌈 Renaissance Researcher (8) 🌱 Topic Pioneer πŸ† Grand Slam 🀝 Dynamic Duo (17) 🧬 Topic Evolution πŸ‘‘ Triple Crown πŸ‘₯ Mega-Team (40) πŸ—ƒοΈ Keyword Collector (176) ⚑ Prolific Year (6) πŸ’Ž Century Club (39) πŸ“ˆ Trend Setter πŸ”₯ Unstoppable (9) ❓ The Questioner (3)

Conferences

EMNLP (5) ICLR (5) ICML (5) NIPS (5) AAAI (4) ACL (4) NAACL (4) IJCAI (3) NSDI (2) ICCV (1) IJCNLP (1) WACV (1)

Top co-authors

Kurt Keutzer (17) Trevor Darrell (8) Zhewei Yao (7) Amir Gholami (5) Michael Mahoney (5) Chunyuan Li (4) Jingyu Yang (3) Stella Biderman (3) Huanjing Yue (3) Thomas Wang (3)

Research topics

Speech & Audio (1) Security & Privacy (1) Privacy (1)

Keywords

vision-language model (4) large language model (4) multimodal learning (4) transformer architecture (3) instruction tuning (3) neural network optimization (3) machine translation (3) model scaling (3) zero-shot generalization (2) language model (2) vision language model (2) transfer learning (2) zero-shot learning (2) reservoir computing (2) cross-lingual transfer (2) image compression (2) model compression (2) data augmentation (2) model adaptation (2) adversarial attack (2)

Papers

Rethinking Bias in Generative Data Augmentation for Medical AI: A Frequency Recalibration Method AAAI 2026 BTS: Harmonizing Specialized Experts into a Generalist LLM EMNLP 2025 AgentBench: Evaluating LLMs as Agents ICLR 2024 Enhancing Large Vision Language Models with Self-Training on Image Comprehension NIPS 2024 Multitask Vision-Language Prompt Tuning WACV 2024 Efficient Screen Content Image Compression via Superpixel-based Content Aggregation and Dynamic Feature Fusion IJCAI 2024 Mixture-of-Experts Meets Instruction Tuning: A Winning Combination for Large Language Models ICLR 2024 MINT-1T: Scaling Open-Source Multimodal Data by 10x: A Multimodal Dataset with One Trillion Tokens NIPS 2024 Aligning Large Multimodal Models with Factually Augmented RLHF ACL 2024 LLM2LLM: Boosting LLMs with Novel Iterative Data Enhancement ACL 2024 SqueezeLLM: Dense-and-Sparse Quantization ICML 2024 Towards Robust Gan-Generated Image Detection: A Multi-View Completion Representation IJCAI 2023 Dec-Adapter: Exploring Efficient Decoder-Side Adapter for Bridging Screen Content and Natural Image Compression ICCV 2023 Crosslingual Generalization through Multitask Finetuning ACL 2023 Poisoning Language Models During Instruction Tuning ICML 2023 Large Language Models are Visual Reasoning Coordinators NIPS 2023 Scaling Vision-Language Models with Sparse Mixture of Experts EMNLP 2023 Multitask Prompted Training Enables Zero-Shot Task Generalization ICLR 2022 K-LITE: Learning Transferable Visual Models with External Knowledge NIPS 2022 What Language Model to Train if You Have One Million GPU Hours? EMNLP 2022 How Much Can CLIP Benefit Vision-and-Language Tasks? ICLR 2022 Staged Training for Transformer Language Models ICML 2022 Exposing the Limits of Video-Text Models through Contrast Sets NAACL 2022 Discovering Non-monotonic Autoregressive Orderings with Variational Inference ICLR 2021 What’s Hidden in a One-layer Randomly Weighted Transformer? EMNLP 2021 Reservoir Transformers ACL 2021 ADAHESSIAN: An Adaptive Second Order Optimizer for Machine Learning AAAI 2021 Reservoir Transformers IJCNLP 2021 Noisy Self-Knowledge Distillation for Text Summarization NAACL 2021 Implicit Transformer Network for Screen Content Image Continuous Super-Resolution NIPS 2021 Q-BERT: Hessian Based Ultra Low Precision Quantization of BERT AAAI 2020 On the Generation of Medical Question-Answer Pairs AAAI 2020 Train Big, Then Compress: Rethinking Model Size for Efficient Training and Inference of Transformers ICML 2020 MAF: Multimodal Alignment Framework for Weakly-Supervised Phrase Grounding EMNLP 2020 Emoji-Powered Representation Learning for Cross-Lingual Sentiment Classification (Extended Abstract) IJCAI 2020 PowerNorm: Rethinking Batch Normalization in Transformers ICML 2020 An annotated dataset of literary entities NAACL 2019 Pragmatically Informative Text Generation NAACL 2019 Inaudible Voice Commands: The Long-Range Attack and Defense NSDI 2018 Bringing IoT to Sports Analytics NSDI 2017