· ai
[Paper] Alterbute: Editing Intrinsic Attributes of Objects in Images
We introduce Alterbute, a diffusion-based method for editing an object's intrinsic attributes in an image. We allow changing color, texture, material, and even ...
-
- · ai
[Paper] MatchTIR: Fine-Grained Supervision for Tool-Integrated Reasoning via Bipartite Matching
Tool-Integrated Reasoning (TIR) empowers large language models (LLMs) to tackle complex tasks by interleaving reasoning steps with external tool interactions. H...
- · ai
[Paper] From One-to-One to Many-to-Many: Dynamic Cross-Layer Injection for Deep Vision-Language Fusion
Vision-Language Models (VLMs) create a severe visual feature bottleneck by using a crude, asymmetric connection that links only the output of the vision encoder...
- · ai
[Paper] High-accuracy and dimension-free sampling with diffusions
Diffusion models have shown remarkable empirical success in sampling from rich multi-modal distributions. Their inference relies on numerically solving a certai...
- · ai
[Paper] See Less, Drive Better: Generalizable End-to-End Autonomous Driving via Foundation Models Stochastic Patch Selection
Recent advances in end-to-end autonomous driving show that policies trained on patch-aligned features extracted from foundation models generalize better to Out-...
- · ai
[Paper] Distributed Perceptron under Bounded Staleness, Partial Participation, and Noisy Communication
We study a semi-asynchronous client-server perceptron trained via iterative parameter mixing (IPM-style averaging): clients run local perceptron updates and a s...
- · ai
[Paper] Grounding Agent Memory in Contextual Intent
Deploying large language models in long-horizon, goal-oriented interactions remains challenging because similar entities and facts recur under different latent ...
- · ai
[Paper] Communication-Efficient and Privacy-Adaptable Mechanism -- a Federated Learning Scheme with Convergence Analysis
Federated learning enables multiple parties to jointly train learning models without sharing their own underlying data, offering a practical pathway to privacy-...
- · ai
[Paper] LIBERTy: A Causal Framework for Benchmarking Concept-Based Explanations of LLMs with Structural Counterfactuals
Concept-based explanations quantify how high-level concepts (e.g., gender or experience) influence model behavior, which is crucial for decision-makers in high-...
- · ai
Data is the only moat
Article URL: https://frontierai.substack.com/p/data-is-your-only-moat Comments URL: https://news.ycombinator.com/item?id=46637328 Points: 4 Comments: 0...
- · ai
[Paper] The Impact of Generative AI on Architectural Conceptual Design: Performance, Creative Self-Efficacy and Cognitive Load
Our study examines how generative AI (GenAI) influences performance, creative self-efficacy, and cognitive load in architectural conceptual design tasks. Thirty...
- · ai
[Paper] Data-driven stochastic reduced-order modeling of parametrized dynamical systems
Modeling complex dynamical systems under varying conditions is computationally intensive, often rendering high-fidelity simulations intractable. Although reduce...