Daily Papers of 2023-10-18

1. BitNet: Scaling 1-bit Transformers for Large Language Models 108 upvotes, #1 of 2023-10-18
2. 4K4D: Real-Time 4D View Synthesis at 4K Resolution 39 upvotes, #2 of 2023-10-18
3. VeRA: Vector-based Random Matrix Adaptation 31 upvotes, #3 of 2023-10-18
4. Set-of-Mark Prompting Unleashes Extraordinary Visual Grounding in GPT-4V 29 upvotes, #4 of 2023-10-18
5. Context-Aware Meta-Learning 17 upvotes, #5 of 2023-10-18
6. EvalCrafter: Benchmarking and Evaluating Large Video Generation Models 17 upvotes, #5 of 2023-10-18
7. Approximating Two-Layer Feedforward Networks for Efficient Transformers 11 upvotes, #7 of 2023-10-18
8. TEQ: Trainable Equivalent Transformation for Quantization of LLMs 10 upvotes, #8 of 2023-10-18
9. LAMP: Learn A Motion Pattern for Few-Shot-Based Video Generation 9 upvotes, #9 of 2023-10-18
10. CrossCodeEval: A Diverse and Multilingual Benchmark for Cross-File Code Completion 4 upvotes, #10 of 2023-10-18

Data: hysts-bot-data/daily-papers-stats and the Daily Papers API. Open data: tardellirs/paper-pulse-data. Sister project: Model Pulse, the download history of every model on the Hub.