· ai
[Paper] Generative Classifiers Avoid Shortcut Solutions
Discriminative approaches to classification often learn shortcuts that hold in-distribution but fail even under minor distribution shift. This failure mode stem...
-
- · ai
[Paper] Modeling Language as a Sequence of Thoughts
Transformer language models can generate strikingly natural text by modeling language as a sequence of tokens. Yet, by relying primarily on surface-level co-occ...
- · ai
[Paper] ResponseRank: Data-Efficient Reward Modeling through Preference Strength Learning
Binary choices, as often used for reinforcement learning from human feedback (RLHF), convey only the direction of a preference. A person may choose apples over ...
- · ai
[Paper] Convergence of the generalization error for deep gradient flow methods for PDEs
The aim of this article is to provide a firm mathematical foundation for the application of deep gradient flow methods (DGFMs) for the solution of (high-dimensi...
- · ai
[Paper] MAMA-Memeia! Multi-Aspect Multi-Agent Collaboration for Depressive Symptoms Identification in Memes
Over the past years, memes have evolved from being exclusively a medium of humorous exchanges to one that allows users to express a range of emotions freely and...
- · ai
[Paper] Diffusion Language Models are Provably Optimal Parallel Samplers
Diffusion language models (DLMs) have emerged as a promising alternative to autoregressive models for faster inference via parallel token generation. We provide...
- · ai
[Paper] FoundationSLAM: Unleashing the Power of Depth Foundation Models for End-to-End Dense Visual SLAM
We present FoundationSLAM, a learning-based monocular dense SLAM system that addresses the absence of geometric consistency in previous flow-based approaches fo...
- · ai
[Paper] Bi-C2R: Bidirectional Continual Compatible Representation for Re-indexing Free Lifelong Person Re-identification
Lifelong person Re-IDentification (L-ReID) exploits sequentially collected data to continuously train and update a ReID model, focusing on the overall performan...
- · ai
[Paper] Basic Inequalities for First-Order Optimization with Applications to Statistical Risk Analysis
We introduce basic inequalities for first-order iterative optimization algorithms, forming a simple and versatile framework that connects implicit and explicit ...
- · ai
[Paper] Classifying long legal documents using short random chunks
Classifying legal documents is a challenge, besides their specialized vocabulary, sometimes they can be very long. This means that feeding full documents to a T...
- · ai
[Paper] PhysTalk: Language-driven Real-time Physics in 3D Gaussian Scenes
Realistic visual simulations are omnipresent, yet their creation requires computing time, rendering, and expert animation knowledge. Open-vocabulary visual effe...
- · ai
[Paper] DarkEQA: Benchmarking Vision-Language Models for Embodied Question Answering in Low-Light Indoor Environments
Vision Language Models (VLMs) are increasingly adopted as central reasoning modules for embodied agents. Existing benchmarks evaluate their capabilities under i...