Decoupled Early Exits for Task-Dependent Compute Allocation in Flow-Matching VLAs
Decoupled early exits across backbone depth, action-expert depth and denoising steps for task-dependent compute allocation in flow-matching VLAs.
Sep 29, 2026
GPTNT: Benchmarking Real-Time Collaboration Between Multimodal Agents on Keep Talking And Nobody Explodes
A benchmark for real-time collaboration between multimodal agents on Keep Talking and Nobody Explodes.
Sep 4, 2026
MIXAR: Scaling Autoregressive Pixel-based Language Models to Multiple Languages and Scripts
A generative pixel-based language model trained on eight languages across multiple scripts.
Apr 13, 2026
VoyagerVision: Investigating the Role of Multi-modal Information for Open-ended Learning Systems
An open-ended multimodal embodied agents for the Minecraft game.
Jan 2, 2026
VLM-RobustBench: A Comprehensive Benchmark for Robustness of Vision-Language Models
A comprehensive study of Vision-Language Models’ behavioural robustness.
Jan 1, 2026
Same Answer, Different Representations: Hidden instability in VLMs
Add the full text or supplementary notes for the publication here using Markdown formatting.
Jan 1, 2026
Retrievit: In-context Retrieval Capabilities of Transformers, State Space Models, and Hybrid Architectures
Add the full text or supplementary notes for the publication here using Markdown formatting.
Jan 1, 2026
AgriPath: A Systematic Exploration of Architectural Trade-offs for Crop Disease Classification
Add the full text or supplementary notes for the publication here using Markdown formatting.
Jan 1, 2026
Movie Facts and Fibs (MF $^ 2$): A Benchmark for Long Movie Understanding
Add the full text or supplementary notes for the publication here using Markdown formatting.
Jan 1, 2025
Visually Grounded Language Learning: A Review of Language Games, Datasets, Tasks, and Models
Jan 1, 2024