Posters

Hallo3D: a tuning-free method resolving 3D generation hallucinations via multi-modal inconsistency detection and mitigation for consistent 3D content.

HairFastGAN achieves realistic and robust hairstyle transfer in near real-time using a novel encoder-based approach, significantly outperforming optimization-based methods.

HairDiffusion uses latent diffusion models and a multi-stage blending technique to achieve vivid, multi-colored hair editing in images, preserving other facial features.

GVKF: A novel method achieves highly efficient and accurate 3D surface reconstruction in open scenes by integrating fast 3D Gaussian splatting with continuous scene representation using kernel regres…

Researchers devised a novel method to accelerate neural network training by guiding the optimization process toward a Simplex Equiangular Tight Frame, exploiting the Neural Collapse phenomenon to enha…

GTG, a novel conditional generative modeling approach, leverages diffusion models to generate high-scoring design trajectories for offline model-based optimization, outperforming existing methods on b…

GUIDE: Real-time human-shaped AI agents achieve up to 30% higher success rates using continuous human feedback, boosted by a parallel training model that mimics human input for continued improvement.

GuardT2I: A novel framework defends text-to-image models against adversarial prompts by translating latent guidance embeddings into natural language, enabling effective adversarial prompt detection wi…

GTBENCH reveals LLMs’ strategic reasoning weaknesses via game-theoretic evaluations, showing strengths in probabilistic scenarios but struggles with deterministic ones; code-pretraining helps.

Generative Trajectory Augmentation (GTA) significantly boosts offline reinforcement learning by generating high-reward trajectories using a conditional diffusion model, enhancing algorithm performance…

GSGAN introduces a hierarchical 3D Gaussian representation for faster, high-quality 3D model generation in GANs, achieving 100x speed improvement over existing methods.

GSDF: A novel dual-branch neural scene representation elegantly resolves the rendering-reconstruction trade-off by synergistically combining 3D Gaussian Splatting and Signed Distance Fields via mutual…

GS-Hider: A novel framework secures 3D Gaussian Splatting by embedding messages in a coupled, secured feature attribute, enabling invisible data hiding and accurate extraction.

Oracle-efficient algorithms conquer online multi-group learning, achieving sublinear regret even with massive, overlapping groups, paving the way for fair and efficient large-scale online systems.

Group Robust Preference Optimization (GRPO) enhances reward-free RLHF by aligning LLMs to diverse group preferences, maximizing worst-case performance, and significantly improving fairness.

Group-and-Shuffle (GS) matrices enable efficient structured orthogonal parametrization, improving parameter and computational efficiency in orthogonal fine-tuning for deep learning.

GrounDiT: Training-free spatial grounding for text-to-image generation using Diffusion Transformers and a novel noisy patch transplantation technique for precise object placement.

Researchers unveil unified architecture for grounding multimodal large language models in actions, showing superior performance with learned tokenization for continuous actions and semantic alignment …

Generative world models enhance multi-agent decision-making by simulating trial-and-error learning, improving answer accuracy and explainability.

Transformers can learn implicit reasoning through ‘grokking’, achieving high accuracy in composition and comparison tasks; however, generalization varies across reasoning types.