Posters

MaVEn: A novel multi-granularity hybrid visual encoding framework significantly boosts MLLM’s multi-image reasoning capabilities by combining discrete and continuous visual representations.

Matryoshka Query Transformer (MQT) empowers large vision-language models with flexible visual token encoding, drastically reducing inference costs while maintaining high accuracy across multiple bench…

MatrixNet learns efficient group representations for improved deep learning on symmetry groups, achieving higher sample efficiency and generalization than existing methods.

Optimal matrix denoising with doubly heteroscedastic noise achieved!

MatFormer: Train one universal model, extract hundreds of accurate submodels for elastic inference!

Sign Stochastic Gradient Descent (SGD) achieves optimal sample complexity for solving k-sparse parity problems, matching Statistical Query lower bounds.

MaskFactory generates high-quality synthetic data for dichotomous image segmentation, improving model training efficiency and accuracy.

Masked Pre-training empowers a universal, fast zero-shot image denoiser!

Masked hard-attention transformers, with strict masking, precisely capture star-free languages, matching the expressive power of linear temporal logic.

This study marries causal representation learning with dynamical systems to enable parameter identification in real-world scientific data, unlocking downstream causal analysis for various applications…

Adaptive MCMC with CNFs accelerates probabilistic inference by combining local and flow-informed transition kernels, achieving state-of-the-art results efficiently.

Researchers developed a new, differentiable score function for learning causal relationships from data that reliably recovers the simplest causal model, even with complex data.

Frugal Flows: Generate realistic causal benchmarks with exact marginal causal effects, enabling robust causal method validation.

Long-context attacks easily manipulate LLMs by feeding hundreds of harmful examples, highlighting a critical vulnerability amplified by larger context windows.

ManiPose: Manifold-constrained multi-hypothesis model solves 3D human pose estimation’s depth ambiguity, outperforming state-of-the-art models in pose consistency.

MAmmoTH2: Harvesting 10M web instructions for enhanced LLM reasoning!

MambaTalk: Efficient holistic gesture synthesis using selective state space models to overcome computational complexity and improve gesture quality.

MambaSCI: Efficient, novel deep learning model reconstructs high-quality quad-Bayer video from compressed snapshots, surpassing existing methods.

MambaLRP enhances explainability of Mamba sequence models by ensuring faithful relevance propagation, achieving state-of-the-art explanation performance, and uncovering model biases.

MambaLLIE: a novel implicit Retinex-aware low-light enhancer using a global-then-local state space, significantly outperforms existing CNN and Transformer-based methods.