· ai
[Paper] Video-CoM: Interactive Video Reasoning via Chain of Manipulations
Recent multimodal large language models (MLLMs) have advanced video understanding, yet most still 'think about videos' ie once a video is encoded, reasoning unf...
-
- · ai
[Paper] Thinking by Doing: Building Efficient World Model Reasoning in LLMs via Multi-turn Interaction
Developing robust world model reasoning is crucial for large language model (LLM) agents to plan and interact in complex environments. While multi-turn interact...
- · ai
[Paper] AnyTalker: Scaling Multi-Person Talking Video Generation with Interactivity Refinement
Recently, multi-person video generation has started to gain prominence. While a few preliminary works have explored audio-driven multi-person talking video gene...
- · ai
[Paper] ThetaEvolve: Test-time Learning on Open Problems
Recent advances in large language models (LLMs) have enabled breakthroughs in mathematical discovery, exemplified by AlphaEvolve, a closed-source system that ev...
- · 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...