Posters

ClavaDDPM synthesizes multi-relational data using cluster-guided diffusion models, efficiently capturing long-range dependencies and outperforming existing methods.

Classifier-Guided Gradient Modulation (CGGM) enhances multimodal learning by balancing the training process, considering both gradient magnitude and direction, leading to consistent performance improv…

SuperClass, a novel vision-language pre-training method, achieves superior performance on various downstream tasks by directly using tokenized raw text as supervised classification labels, eliminating…

Classification Diffusion Models (CDMs) revolutionize density ratio estimation by integrating the strengths of diffusion models and classifiers, achieving state-of-the-art image generation and likeliho…

Zero-shot learning models often fail in real-world scenarios due to unseen class distribution shifts. This work introduces a novel algorithm that learns robust representations by creating synthetic d…

CLAP4CLIP enhances vision-language model continual learning by using probabilistic finetuning, improving performance and uncertainty estimation.

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…

CIFD, a novel knowledge distillation method, drastically cuts training costs while boosting performance, particularly for large datasets, by using Rate-Distortion Modules instead of Teacher Assistants…

ChronoEpilogi efficiently finds all minimal sets of time-series variables optimally predicting a target, improving forecasting while providing crucial insights for knowledge discovery and causal model…

Chimera: a novel 2D state space model effectively captures complex multivariate time series dependencies, achieving superior forecasting, classification, and anomaly detection.

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.

ChatCam empowers users to control cameras via natural language, using CineGPT for text-conditioned trajectory generation and an Anchor Determinator for precise placement, enabling high-quality video r…

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

CHASE: A novel method for skeleton-based multi-entity action recognition that cleverly adapts skeleton positions to minimize data bias and boost accuracy.

Boosting in-distribution generalization is achieved by strategically altering the training data distribution to reduce simplicity bias and promote uniform feature learning.

Researchers developed novel algorithms to generate structurally diverse graphs, improving graph algorithm testing and neural network evaluation.

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…