Posters

Forget-free graph class-incremental learning achieved via a novel task profiling and prompting approach, significantly outperforming state-of-the-art methods.

ReplaceAnything3D (RAM3D) revolutionizes 3D scene editing with a text-guided, multi-view consistent approach for seamlessly replacing or adding 3D objects in complex scenes.

MRConv: Reparameterized multi-resolution convolutions efficiently model long sequences, improving performance across various data modalities.

RENOVATE renovates open-vocabulary segmentation benchmarks by automatically improving class names, leading to stronger models and more accurate evaluations.

ReNO: Boost one-step text-to-image models by cleverly optimizing initial noise using reward signals, achieving state-of-the-art results efficiently.

KATE: A new scale-invariant AdaGrad variant achieves state-of-the-art convergence without square roots, outperforming AdaGrad and matching/exceeding Adam’s performance.

ReMoDetect leverages reward models to identify and classify LLM-generated text. By using continual preference fine-tuning and incorporating human/LLM mixed text, ReMoDetect achieves state-of-the-art p…

Remix-DiT: Boosting diffusion model image generation quality by cleverly mixing smaller basis models into numerous specialized denoisers, improving efficiency and lowering costs!

ReMAP repurposes able-bodied motion prediction models for limb-impaired patients using network inversion and retrieval-augmented mapping, significantly improving motion forecasting.

ReLIZO boosts zeroth-order optimization by cleverly reusing past queries, drastically cutting computation costs while maintaining gradient estimation accuracy.

Relationship Prompt Network (RPN) achieves state-of-the-art open-vocabulary semantic segmentation using only prompt learning and a Vision-Language Model (VLM), eliminating the need for expensive segme…

RABBit: A novel Branch-and-Bound verifier for precise relational verification of Deep Neural Networks, achieving substantial precision gains over current state-of-the-art baselines.

Relational Concept Bottleneck Models (R-CBMs) merge interpretable CBMs with powerful GNNs for high-performing, explainable relational deep learning.

Neural Episodic Control’s differentiable dictionary is shown to be a Universal Hopfield Network, enabling improved performance and a novel evaluation criterion.

This paper introduces a novel framework for classification with rejection by learning density ratios between data and idealized distributions, improving model robustness and accuracy.

POAD enhances LLM agents by decomposing language agent optimization to the token level, achieving finer-grained credit assignment and improved learning efficiency and generalization.

Reinforcement learning with complex objectives made easy: This paper introduces an optimality-preserving translation to reduce problems with Linear Temporal Logic (LTL) objectives to standard average …

Provably efficient RL algorithms are designed to utilize immediate reward or transition information, significantly improving reward collection in unknown environments.

Boosting RL data efficiency for continuous control, this paper advocates Euclidean data augmentation using limb-based state features, significantly improving performance across various tasks.

Safe reinforcement learning is achieved via RL-AR, an algorithm that combines a safe policy with an RL policy using a focus module, ensuring safety during training while achieving competitive performa…