Posters

Reinforcement learning refines existing macro placements, enhancing chip design by improving power, performance, and area (PPA) metrics and integrating the often-overlooked metric of regularity.

Reinforcement Learning guides a novel semi-supervised learning method, improving model performance by adaptively balancing labeled and unlabeled data.

Reinforced Cross-Domain Knowledge Distillation (RCD-KD) dynamically selects target samples for efficient knowledge transfer from a complex teacher model to a compact student model, achieving superior …

InfoScissors defends collaborative inference from data leakage by cleverly reducing the mutual information between model outputs and sensitive device data, thus ensuring robust privacy without comprom…

Regularizing hidden states improves reward model generalization in RLHF for LLMs, boosting accuracy and mitigating over-optimization.

RegQ: A novel regularized Q-learning algorithm ensures convergence with linear function approximation, solving a long-standing instability problem in reinforcement learning.

A novel regularized conditional diffusion model enables effective multi-task preference alignment in sequential decision-making by learning unified preference representations and maximizing mutual inf…

RAMDA: a new algorithm ensures efficient training of structured neural networks by achieving optimal structure and outstanding predictive performance.

ReGS: Real-time reference-based 3D scene stylization using Gaussian Splatting for high-fidelity texture editing and free-view navigation.

This research shows how to improve Stackelberg game strategies by considering side information, achieving no-regret learning in online settings with stochastic contexts or followers.

Ensuring fair regression predictions without using sensitive attributes? This paper presents a novel post-processing algorithm, achieving demographic parity with strong theoretical guarantees and comp…

RegExplainer unveils a novel method for interpreting graph neural networks in regression tasks, bridging the explanation gap by addressing distribution shifts and tackling continuously ordered decisio…

LLM refusal is surprisingly mediated by a single, easily manipulated direction in the model’s activation space.

COPPER enhances LLM-based multi-agent collaboration via a self-reflection mechanism and counterfactual PPO. It improves reflection quality, alleviates credit assignment issues, and shows strong perfo…

ReFIR enhances Large Restoration Models’ accuracy by incorporating retrieved images as external knowledge, mitigating hallucination without retraining.

RefHuman: a new dataset and UniPHD model achieve state-of-the-art referring human pose and mask estimation in the wild, using text or positional prompts.

RefFormer boosts visual grounding accuracy by intelligently adapting queries using multi-level image features, effectively guiding the decoder towards the target object.

Reference Trustable Decoding (RTD) revolutionizes large language model adaptation by offering a training-free method, enabling efficient and cost-effective task adaptation without parameter adjustment…

RefDrop: A training-free method enhances image and video generation consistency by directly controlling the influence of reference features on the diffusion process, enabling precise manipulation of c…

ReF-LDM uses reference images to improve the accuracy of face image restoration, achieving high-quality results faithful to the subject’s true appearance.