Posters

LACIE: Listener-aware finetuning improves LLM confidence calibration, reducing incorrect answers accepted by human listeners by 47% while maintaining correct answer acceptance.

Ignorance is bliss: A new framework shows ignoring label noise in multi-class classification can achieve state-of-the-art performance, especially when using self-supervised feature extraction.

Bridging the accuracy gap in online continual learning caused by label delays, a new framework with Importance Weighted Memory Sampling prioritizes relevant memory samples, significantly outperforming…

L4GM: The first 4D model generating high-quality animated 3D objects from single-view videos in a single feed-forward pass.

L-TTA: A lightweight test-time adaptation method using a versatile stem layer minimizes channel-wise uncertainty for rapid and memory-efficient adaptation to new domains.

KVQuant achieves <0.1 perplexity degradation with 3-bit quantization in LLMs by using per-channel key quantization, pre-RoPE quantization, and non-uniform quantization, enabling 10M context length inf…

Boost LLM inference speed 1.4-3.5x by using Coupled Quantization (CQ) to compress KV cache down to 1 bit per channel, while preserving model accuracy.

Kraken: A new Transformer architecture boosts multi-device inference speed by 35.6% by cleverly overlapping communication with computation.

KptLLM: A novel multimodal model leverages LLMs for superior keypoint comprehension, outperforming existing methods in various benchmarks.

KOALA: New efficient text-to-image diffusion models achieving 4x speed and 69% size reduction of SDXL, generating 1024px images on consumer GPUs with 8GB VRAM.

KEDGN, a novel graph neural network, leverages medical knowledge to model variable-specific temporal dependencies and dynamic inter-variable correlations in irregularly sampled medical time series, si…

Novel intermediate variables regularization boosts knowledge graph completion!

aTLAS: a novel parameter-efficient fine-tuning method using learned anisotropic scaling of task vectors for enhanced knowledge composition and transfer.

Researchers unveil ‘knowledge circuits’ within LLMs, revealing how knowledge is collaboratively encoded and utilized, leading to improved LLM design and interpretations of model behavior.

KnowGPT: A novel framework boosts Large Language Model accuracy by intelligently integrating knowledge graphs, significantly reducing factual errors and achieving near-human performance on benchmark d…

KG-FIT boosts knowledge graph embedding by smartly integrating open-world knowledge from LLMs, achieving significant performance gains.

KFNN dynamically determines optimal neighborhood sizes for label integration in crowdsourcing, significantly boosting accuracy and robustness, especially with limited noisy labels.

Key-Grid: An unsupervised 3D keypoint detector achieving state-of-the-art semantic consistency and accuracy for both rigid and deformable objects using novel grid heatmap features.

Novel optimistic RL algorithm using kernel methods achieves no-regret performance in the challenging infinite-horizon average-reward setting.

Boosting Out-of-Distribution Detection with Kernel PCA!