5arXiv cs.AI (Artificial Intelligence)·
OpenCoF: Framework for Chain-of-Frame reasoning via video generation
Researchers introduce OpenCoF, a framework that treats video generation as a reasoning substrate — where logical inference unfolds across temporally connected frames (Chain-of-Frame, CoF) rather than text tokens. The work includes OpenCoF-17K, a 17K-sample reasoning video dataset spanning 11 task families, and Wan-CoF, a fine-tuned video model built on Wan2.2-I2V-A14B that achieves gains on four video reasoning benchmarks. The paper also explores augmenting the model with visual and textual reasoning tokens to capture low-level visual cues and high-level semantic priors. All artifacts are open-sourced.
Related guides (2)
Related events (8)
IV-CoT: Implicit Visual Chain-of-Thought for Structure-Aware Text-to-Image Generation
Researchers propose Implicit Visual Chain-of-Thought (IV-CoT), a latent visual reasoning framework that decomposes visual conditioning queries into a structural-to-semantic cascade for text-to-image generation. The method uses training-only sketch supervision to guide structural queries without requiring sketch extraction at inference time, enabling implicit CoT reasoning in a single forward pass. IV-CoT achieves improved results on GenEval and T2I-CompBench benchmarks, targeting persistent weaknesses in multimodal LLMs around object counts, spatial relations, and attribute binding.
Systematic evaluation reveals limits of multimodal Chain-of-Thought reasoning across perception and reasoning tasks
A new arXiv paper evaluates multimodal Chain-of-Thought (CoT) reasoning across 12 tasks using 22 models (14 non-reasoning, 8 reasoning), finding that CoT is not universally beneficial: it hurts performance on perception tasks like visual grounding and object counting while helping mathematical and scientific reasoning. The study identifies a 'Look Light, Think Heavy' pattern where visual reflection consistently diminishes during reasoning chains even as verbal reflection fluctuates, pointing to deep visual introspection as a key unsolved bottleneck. Open-source multimodal reasoning models show only marginal overall gains, likely due to overemphasis on mathematical reasoning during training.
Reasoning models struggle to control their chains of thought, and that's good
OpenAI introduces CoT-Control, a framework for evaluating how well reasoning models can deliberately manipulate or suppress their chain-of-thought outputs. The finding that models struggle to control their CoT is framed as a positive safety property, reinforcing the argument that visible reasoning traces serve as a meaningful monitorability safeguard. This contributes to ongoing research on whether chain-of-thought transparency is a reliable alignment and oversight tool.
Lumos-Nexus: Efficient Frequency Bridging for Reasoning-Driven Video Generation
Lumos-Nexus is a training-efficient unified video generation framework that decouples training and inference to achieve high visual fidelity without prohibitive compute costs. During training, a lightweight generator is aligned with an understanding block; at inference, Unified Progressive Frequency Bridging (UPFB) hands off generation to a high-capacity pretrained generator in a shared latent space for coarse-to-fine refinement. The authors also introduce VR-Bench, a new benchmark for evaluating reasoning-driven video generation. Code and models are publicly released.
Introducing the Open Chain of Thought Leaderboard
Hugging Face has launched the Open Chain of Thought Leaderboard, a benchmarking platform specifically designed to evaluate open-weight language models on chain-of-thought reasoning capabilities. The leaderboard tracks model performance across reasoning-intensive tasks that require multi-step inference. This initiative aims to provide standardized, reproducible comparisons of CoT reasoning quality across the open-weights ecosystem.
ReaORE: Reasoning-guided progressive framework for open relation extraction using large reasoning models
ReaORE is a new framework for Open Relation Extraction (OpenRE) that uses a coarse-to-fine reasoning pipeline to identify unseen relation types between entities in unstructured text. The approach combines a relation filtering stage (using multi-aspect reasoning and embedding-based similarity) with a fine-grained comparative reasoning stage for relation prediction. The authors report that ReaORE outperforms existing baselines on two standard OpenRE benchmarks, addressing limitations of both clustering-based and direct LLM generation approaches.
OneReason: Activating Chain-of-Thought Reasoning in Generative Recommendation Models
Researchers from the OneRec team introduce OneReason, a framework for enabling reasoning capabilities in generative recommendation models deployed across short-video, live-streaming, advertising, and e-commerce. The work identifies a key failure mode — that naive thinking-mode integration does not outperform non-thinking baselines — and diagnoses this as a deficit in two factors: itemic token perception and user behavior cognition. The proposed solution combines perception-focused pre-training, a three-level cognition-enhanced CoT format for supervised fine-tuning, and a specialize-then-unify RL training recipe.
Survey: Human-View Video Understanding with MLLMs — Watch, Remember, Reason Framework
A new arXiv survey paper proposes a unified 'human-view' framework for analyzing multimodal LLM-based video understanding, organized around three functional abilities: watching (perception), remembering (memory), and reasoning. The authors introduce a formulation characterizing video understanding systems by perceptual representations, memory states, reasoning traces, and predictions, then survey methods, datasets, and benchmarks across these dimensions. The work covers challenges including spatio-temporal perception, long-video processing, streaming understanding, and faithful reasoning, with application domains spanning egocentric, sports, medical, and narrative video.