Posters

Algorithmic monoculture harms applicant selection and market efficiency; this paper introduces a model to analyze its effects in two-sided matching markets.

MonkeySee reconstructs natural images from macaque brain signals with high accuracy using a novel CNN decoder, advancing neural decoding and offering insights into visual perception.

MoMu-Diffusion: a novel framework that learns long-term motion-music synchronization, generating realistic and beat-matched sequences surpassing existing methods.

MomentumSMoE boosts Sparse Mixture of Experts’ (SMoE) performance by integrating momentum, resulting in more stable training and robust models.

MoME, a novel Mixture of Multimodal Experts, significantly improves generalist Multimodal Large Language Models (MLLMs) by mitigating task interference through specialized vision and language experts,…

f-RAG: A novel fragment-based molecular generation framework boosts drug discovery by combining retrieval augmentation with a generative model, enabling exploration beyond existing fragments and signi…

MoLE: Mixture of Low-rank Experts enhances human-centric text-to-image diffusion models by using low-rank modules trained on high-quality face and hand datasets to improve the realism of faces and han…

MoGU: A framework dynamically balances safety and usability in LLMs by routing benign and malicious instructions to different LLM variants, leading to safer, more useful responses.

MoGenTS revolutionizes human motion generation by quantizing individual joints into 2D tokens, enabling efficient spatial-temporal modeling and significantly outperforming existing methods.

MoEUT: Mixture-of-Experts Universal Transformers significantly improves the compute efficiency of Universal Transformers, making them competitive with standard Transformers in large-scale language mod…

MoE Jetpack efficiently transforms readily available dense checkpoints into high-performing MoE models, drastically accelerating convergence and improving accuracy.

gpSLDS, a novel model, balances expressiveness and interpretability in modeling complex neural dynamics by combining Gaussian processes with switching linear dynamical systems, improving accuracy and …

LoRa-PI: a model-free RL algorithm learns and exploits low-rank MDP structures for order-optimal sample complexity, achieving ε-optimal policies with O(poly(A)) samples.

Model-Based Transfer Learning (MBTL) boosts deep RL sample efficiency by strategically selecting training tasks, achieving up to 50x improvement over traditional methods.

Model-Based Diffusion (MBD) uses diffusion processes and model information for data-free trajectory optimization, outperforming existing methods on complex tasks.

Model Sensitivity Aware Continual Learning (MACL) tackles the CL challenge by optimizing model performance based on parameter distribution, achieving superior old knowledge retention and new task perf…

Counterfactual Clamping Attack (CCA) improves model reconstruction using counterfactual explanations by leveraging decision boundary proximity, offering theoretical guarantees and enhanced fidelity.

Model LEGO (MDA) revolutionizes deep learning by enabling the creation of new models by assembling and disassembling task-aware components from pre-trained models, eliminating the need for retraining.

MxDNA: Model learns optimal DNA tokenization via gradient descent, outperforming existing methods.

Training AI models on AI-generated data leads to performance degradation, known as model collapse. This paper offers analytical formulas that precisely quantify this effect in high-dimensional regress…