arXiv:2605.18804v1 Announce Type: new Abstract: We propose Adaptive Multi-Scale Goodness Aggregation (AMSGA), a novel extension of the Forward-Forward (FF) algorithm designed to improve stability, robustness, and generalization in local-learning neural networks. AMSGA addresses several limitations of the original FF framework…
arXiv:2605.19990v1 Announce Type: cross Abstract: Visual-Inertial Odometry(VIO), which is critical to mobile robot navigation, uses cameras with a large number of pixels. Capturing and processing camera images requires significant resources. This work presents a minimalist approach to planar odometry, demonstrating…
arXiv:2605.18807v1 Announce Type: new Abstract: Encoder-decoder models offer substantial inference-time savings over decoder-only models, but their pretraining objectives suffer from sparse supervision and dynamic sequence lengths, keeping them out of practice at scale. We propose block-based double decoders, a novel…
arXiv:2510.09872v2 Announce Type: replace Abstract: Training web agents to navigate complex, real-world websites requires them to master $textit{subtasks}$ – short-horizon interactions on multiple UI components (e.g., choosing the correct date in a date picker, or scrolling in a container to…
arXiv:2605.18808v1 Announce Type: new Abstract: We characterize a compositional architecture of literary primitives in two instruction-tuned large language models (Llama 3.1 8B-Instruct and Gemma 2 9B-IT) via sparse autoencoders on mid-depth residual streams. Four feature classes emerge: naming-gates that promote…
arXiv:2602.10933v2 Announce Type: replace Abstract: Continuous-time generative models have achieved remarkable success in image restoration and synthesis. However, controlling the composition of multiple pre-trained models remains an open challenge. Current approaches largely treat composition as an algebraic composition of probability…
arXiv:2605.18809v1 Announce Type: new Abstract: General-sum multi-agent learning is often governed by a stacked update field in which each agent’s policy update changes the optimization landscape faced by the others. This coupling can entangle an integrable component of collective improvement…
arXiv:2605.15532v2 Announce Type: replace Abstract: Distillation enables compact Vision-Language Models (VLMs) to obtain strong reasoning capabilities, yet the prompts driving this process are typically chosen via simple heuristics or aggregated from off-the-shelf datasets. We reveal a critical inefficiency in this…
arXiv:2605.18810v1 Announce Type: new Abstract: Speculative decoding accelerates LLM inference by having a small drafter propose tokens that a larger target model verifies in parallel. Recent diffusion-based parallel drafters such as DFlash predict the full B-token block in one forward…
arXiv:2505.18191v2 Announce Type: replace-cross Abstract: Reliable automatic seizure detection from long-term electroencephalography (EEG) remains an unsolved challenge, as current models often fail to generalize across patients or clinical settings. Manual EEG review still is the standard of care, highlighting the…
