Natural Language Processing

CoMERA achieves 2-3x faster AI model training via rank-adaptive tensor optimization, significantly improving both computing and memory efficiency.

LE-SINR combines Wikipedia species descriptions with citizen science observations to create accurate species range maps, even with limited data, outperforming existing methods.

COLD framework rigorously evaluates LLMs’ causal reasoning in everyday scenarios using 9 million causal queries derived from human-generated scripts of daily activities.

CORY: a novel multi-agent RL framework boosts LLM fine-tuning!

Code Rosetta pushes the boundaries of unsupervised code translation by introducing the first encoder-decoder model that efficiently translates between programming languages and their parallel HPC exte…

New program synthesis method, REX, leverages Thompson Sampling to balance exploration and exploitation in iterative LLM code refinement, solving more problems with fewer model calls.

CLUES: Collaborative learning selects high-quality private data for LLM fine-tuning via training dynamics, significantly boosting performance in diverse domains.

CigTime generates corrective motion instructions from motion pairs using motion editing and large language models. This innovative approach improves upon baselines by leveraging motion triplets for f…

CherryQ, a novel quantization method, leverages parameter heterogeneity in LLMs to achieve superior performance by selectively quantizing less critical parameters while preserving essential ones.

ChatTracker boosts visual tracking by intelligently using a large language model to refine object descriptions, achieving performance on par with state-of-the-art methods.

ChatQA, a new suite of models, outperforms GPT-4 in conversational QA and RAG by using a two-stage instruction tuning method and a cost-effective dense retriever.

Chat-Scene: Bridging 3D scenes and LLMs using object identifiers for efficient, object-level interaction and improved scene comprehension.

LLMs can reason effectively without prompting by simply adjusting the decoding process to reveal inherent chain-of-thought paths.

Chain of Thought prompting in LLMs offers limited generalizability, providing performance gains only when prompts are highly specific to problem types; highlighting a critical trade-off between perfor…

Chain of Preference Optimization (CPO) dramatically improves LLM reasoning by leveraging ToT’s search tree for efficient fine-tuning, achieving similar or better performance with significantly reduced…

Chain-of-Agents (CoA) framework uses multi-agent collaboration to efficiently process long contexts for LLMs, significantly improving performance on various tasks.

LLMs surprisingly master complex logic puzzles like Sudoku and Zebra puzzles after training on strategically ordered solution steps, revealing hidden reasoning abilities.

Cascade Speculative Drafting (CS Drafting) dramatically speeds up large language model inference by using a multi-stage drafting process, optimizing both time allocation and autoregressive generation.

Smaller language models can learn skill composition from limited examples, substantially improving their ability to combine skills in novel ways through fine-tuning.

LLMs can improve reasoning by teaching weaker models, a process called Learning by Teaching (LbT), as shown in this preliminary study. LbT enhances not just student models, but also the teacher model…