· ai
[Paper] Visual Generation Tuning
Large Vision Language Models (VLMs) effectively bridge the modality gap through extensive pretraining, acquiring sophisticated visual representations aligned wi...
-
- · ai
[Paper] SmallWorlds: Assessing Dynamics Understanding of World Models in Isolated Environments
Current world models lack a unified and controlled setting for systematic evaluation, making it difficult to assess whether they truly capture the underlying ru...
- · ai
[Paper] The Price of Progress: Algorithmic Efficiency and the Falling Cost of AI Inference
Language models have seen enormous progress on advanced benchmarks in recent years, but much of this progress has only been possible by using more costly models...
- · ai
[Paper] Object-Centric Data Synthesis for Category-level Object Detection
Deep learning approaches to object detection have achieved reliable detection of specific object classes in images. However, extending a model's detection capab...
- · ai
[Paper] Physics-Informed Neural Networks for Thermophysical Property Retrieval
Inverse heat problems refer to the estimation of material thermophysical properties given observed or known heat diffusion behaviour. Inverse heat problems have...
- · 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] ASTRO: Adaptive Stitching via Dynamics-Guided Trajectory Rollouts
Offline reinforcement learning (RL) enables agents to learn optimal policies from pre-collected datasets. However, datasets containing suboptimal and fragmented...
- · 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] Evaluating LLMs for One-Shot Patching of Real and Artificial Vulnerabilities
Automated vulnerability patching is crucial for software security, and recent advancements in Large Language Models (LLMs) present promising capabilities for au...