Posters

MGF: Mixed Gaussian Flow enhances trajectory prediction by using a mixed Gaussian prior, achieving state-of-the-art diversity and alignment accuracy.

MG-Net dynamically designs optimal mixer Hamiltonians for QAOA, overcoming the limitation of fixed-depth quantum circuits and significantly improving approximation ratios.

Novel metric space magnitude measures rigorously quantify the diversity of latent representations across multiple scales, showing superior performance in detecting mode collapse and characterizing emb…

Humans as landmarks: A novel zero-shot monocular metric depth estimation method leverages generative models and human mesh recovery to transfer metric scale information, achieving superior generalizat…

METRIC FLOW MATCHING (MFM) generates smooth interpolations on data manifolds by minimizing kinetic energy, outperforming Euclidean methods and achieving state-of-the-art results in single-cell traject…

Meteor: Mamba-based Traversal of Rationale achieves significant vision-language improvements by efficiently embedding multifaceted rationales in a large language model, without scaling the model or us…

MetaUAS achieves universal visual anomaly segmentation using only one normal image prompt via a pure vision model, surpassing previous zero-shot, few-shot, and full-shot methods.

MetaCURL: First algorithm for non-stationary Concave Utility Reinforcement Learning (CURL), achieving near-optimal dynamic regret by using a meta-algorithm and sleeping experts framework.

LLMs gain math skills via prompt-guided skill labeling and exemplar selection, significantly boosting accuracy.

MetaAligner: a novel, policy-agnostic, and generalizable method for efficiently aligning LLMs to multiple objectives, even unseen ones, achieving significant and balanced improvements while saving up …

Provable near-optimality in meta-RL is achieved using a novel bilevel optimization framework and universal policy adaptation algorithm.

MetaNCoV: Learn data-driven priors via non-injective change of variables for enhanced few-shot learning.

Meta-Exploiting Frequency Prior enhances cross-domain few-shot learning by leveraging image frequency decomposition and consistency priors to improve model generalization and efficiency.

Meta-DT: Offline meta-RL masters unseen tasks via conditional sequence modeling and world model disentanglement, showcasing superior few-shot and zero-shot generalization.

Meta-DiffuB enhances sequence-to-sequence text diffusion models by using meta-exploration to learn a contextualized noise schedule, resulting in state-of-the-art performance.

Meta-Controller: A novel few-shot behavior cloning framework enables robots to generalize to unseen embodiments and tasks using only a few reward-free demonstrations, showcasing superior few-shot gene…

Meta 3D AssetGen: High-quality text-to-mesh generation with realistic PBR materials and lighting, exceeding prior methods in speed and accuracy.

MeshXL: Autoregressively generating high-quality 3D meshes using a novel Neural Coordinate Field (NeurCF) representation and large language model approaches.

Mesa-Extrapolation enhances LLM extrapolation using a novel weave position encoding method, boosting performance while significantly reducing memory and inference time.

MemVLT: Adaptive Vision-Language Tracking leverages memory to generate dynamic prompts, surpassing existing methods by adapting to changing target appearances.