arXiv AI
Beyond the Sequentiality Bottleneck: A Hybrid Diffusion-Autoregressive Framework for Efficient Multimodal Reasoning
Read the original on arXiv AI →The Flow has not summarised this story yet — read it at arXiv AI.
Related stories
Hugging Face Trending Papers
5d ago
Beyond the Sequentiality Bottleneck: A Hybrid Diffusion-Autoregressive Framework for Efficient Multimodal Reasoning
Autoregressive models (ARMs) face a "Sequentiality Bottleneck" in reasoning, while diffusion language models (DLMs) offer parallelism but lack semantic coherence. To addresses both limitations, we pro...
arXiv Machine Learning
Jun 16
DLWM: Diverse Latent World Models for Efficient Multimodal Reasoning
arXiv:2606. 15160v1 Announce Type: cross Abstract: Reasoning capabilities of multimodal large language models (MLLMs) have improved considerably in recent years.
arXiv AI
Oct 2
Selection-Based Structured Reasoning: Toward Efficient Multimodal Search Agents
Selection-Based Structured Reasoning (SSR) is a framework that replaces free-form reasoning with the selection of pre-specified natural‑language reasoning candidates, allowing multimodal agents to choose from a set of reusable high‑level reasoning traces. By scoring these candidates in parallel using a shared context KV cache, SSR eliminates the need for an auxiliary task head and reduces inference cost. Experiments on seven multimodal search benchmarks with 2B and 4B models show that SSR maintains competitive success rates while cutting per‑turn reasoning latency by over 90% and overall inference latency by 28–54%.
arXiv Machine Learning
Sep 14
CanvasAnneal: Curriculum Reinforcement Learning for Diffusion Language Models
CanvasAnneal is a curriculum‑guided reinforcement learning framework designed to improve Diffusion Language Models (DLMs) on complex reasoning and tool‑use tasks. It starts training by injecting reasoning traces from a stronger teacher model into the diffusion canvas, then gradually reduces this guidance so the model learns to generate reasoning independently. Experiments on mathematical reasoning and tool‑use benchmarks show that CanvasAnneal outperforms standard diffusion RL methods such as diffu‑GRPO on tasks like MATH500, Countdown, and Tau2, and accelerates reward improvement, though the gains vary by task.
arXiv Machine Learning
Jun 16
Think Less, Act Early: Reinforced Latent Reasoning with Early Exit in Vision-Language-Action Models
arXiv:2606. 15099v1 Announce Type: cross Abstract: Existing Vision-Language-Action (VLA) models predominantly rely on explicit Chain-of-Thought (CoT) reasoning to bridge perception and action.
arXiv Computer Vision
Oct 15
CASHEW: Stabilizing Multimodal Reasoning via Iterative Trajectory Aggregation
arXiv:2601.08010v4 Announce Type: replace Abstract: Vision-language models achieve strong performance across a wide range of multimodal understanding and reasoning tasks, yet their multi-step reasoni...