· ai
[Paper] Provable Benefits of Sinusoidal Activation for Modular Addition
This paper studies the role of activation functions in learning modular addition with two-layer neural networks. We first establish a sharp expressivity gap: si...
-
- · ai
[Paper] Accelerated Execution of Bayesian Neural Networks using a Single Probabilistic Forward Pass and Code Generation
Machine learning models perform well across domains such as diagnostics, weather forecasting, NLP, and autonomous driving, but their limited uncertainty handlin...
- · ai
[Paper] Towards Continuous Intelligence Growth: Self-Training, Continual Learning, and Dual-Scale Memory in SuperIntelliAgent
We introduce SuperIntelliAgent, an agentic learning framework that couples a trainable small diffusion model (the learner) with a frozen large language model (t...
- · ai
[Paper] Hunyuan-GameCraft-2: Instruction-following Interactive Game World Model
Recent advances in generative world models have enabled remarkable progress in creating open-ended game environments, evolving from static scene synthesis towar...
- · ai
[Paper] DisMo: Disentangled Motion Representations for Open-World Motion Transfer
Recent advances in text-to-video (T2V) and image-to-video (I2V) models, have enabled the creation of visually compelling and dynamic videos from simple textual ...
- · ai
[Paper] MANTA: Physics-Informed Generalized Underwater Object Tracking
Underwater object tracking is challenging due to wavelength dependent attenuation and scattering, which severely distort appearance across depths and water cond...
- · ai
[Paper] LFM2 Technical Report
We present LFM2, a family of Liquid Foundation Models designed for efficient on-device deployment and strong task capabilities. Using hardware-in-the-loop archi...
- · ai
[Paper] Quantized-Tinyllava: a new multimodal foundation model enables efficient split learning
Split learning is well known as a method for resolving data privacy concerns by training a model on distributed devices, thereby avoiding data sharing that rais...
- · ai
[Paper] Ambiguity Awareness Optimization: Towards Semantic Disambiguation for Direct Preference Optimization
Direct Preference Optimization (DPO) is a widely used reinforcement learning from human feedback (RLHF) method across various domains. Recent research has incre...
- · ai
[Paper] Learning-Augmented Online Bipartite Matching in the Random Arrival Order Model
We study the online unweighted bipartite matching problem in the random arrival order model, with $n$ offline and $n$ online vertices, in the learning-augmented...
- · ai
[Paper] VQRAE: Representation Quantization Autoencoders for Multimodal Understanding, Generation and Reconstruction
Unifying multimodal understanding, generation and reconstruction representation in a single tokenizer remains a key challenge in building unified models. Previo...
- · ai
[Paper] Optimizing Multimodal Language Models through Attention-based Interpretability
Modern large language models become multimodal, analyzing various data formats like text and images. While fine-tuning is effective for adapting these multimoda...