Notable data and AI papers

Papers627Labs45

627 papers · 45 labs

Latent Implicit Visual Reasoning research paper by UC Berkeley, 2025

UC Berkeley · Reasoning · Dec 24, 2025 · 19 citations · 60 upvotes · unverified

Read on arXiv

What it shows

This paper introduces a task-agnostic mechanism for models to discover and use visual reasoning tokens without explicit supervision.

By Kelvin Li, Chuyi Shang, Leonid Karlinsky and 3 more · arXiv 2512.21218 · PDF

UnverifiedSummarised by a model from the abstract; not yet checked by hand.

More from UC Berkeley

All 14
ArchitecturesUnverifiedOct 14, 2026Correction Training for Diffusion ModelsThis method adds a correction step to diffusion models to fix errors that accumulate during the image generation process.UC Berkeley42 upvotesRead →Multimodal and roboticsUnverifiedSep 29, 2026OmniTaskonomy: When Does Visual Generation Improve Visual Understanding?This paper maps how visual generation tasks improve visual understanding capabilities, revealing specific task-dependent transfer benefits.UC Berkeley57 upvotesRead →Inference and efficiencyUnverifiedAug 17, 2026FreeToken: Efficient Edge-Native MoE Serving with Bandwidth-Adaptive ExecutionFreeToken is an edge-native Mixture-of-Experts serving system that dynamically maps computation and model state onto heterogeneous local hardware to run large open-weight models on personal machines.UC Berkeley8 citations86 upvotesRead →Agents and evaluationUnverifiedJun 17, 2026Playful Agentic Robot LearningEmbodied robots learn reusable skills through self-directed play and exploration, then apply these skills to improve performance on downstream tasks without additional training.UC Berkeley37 citations49 upvotesRead →Agents and evaluationJun 3, 2026Agents' Last ExamOver 1,000 real, checkable professional tasks written with 250+ industry experts; the hardest tier is far from solved.UC Berkeley42 citations393 upvotesRead →Inference and efficiencyUnverifiedMar 10, 2026Flash-KMeans: Fast and Memory-Efficient Exact K-MeansFlash-kmeans enables efficient online k-means clustering on GPUs through novel kernel-level optimizations that eliminate I/O bottlenecks and reduce atomic write contention.UC Berkeley16 citations64 upvotesRead →Foundation modelsUnverifiedFeb 26, 2026dLLM: Simple Diffusion Language ModelingA unified open-source framework is presented that standardizes core components of diffusion language modeling for reproduction, customization, and accessible development of both large and small models.UC Berkeley18 citations136 upvotesRead →Inference and efficiencyUnverifiedFeb 13, 2026SLA2: Sparse-Linear Attention with Learnable Routing and QATSLA2 improves sparse-linear attention in diffusion models by introducing a learnable router, direct attention formulation, and quantization-aware fine-tuning for enhanced efficiency and quality.UC Berkeley1 citations59 upvotesRead →

Other reasoning papers

Topic
ReasoningJan 28, 2022Chain-of-Thought Prompting Elicits Reasoning in Large Language ModelsAsking a model to write out its intermediate steps (chain of thought) sharply improves its math and logic answers.Google23.8k citations16 upvotesRead →ReasoningUnverifiedFeb 5, 2024DeepSeekMath: Pushing the Limits of Mathematical Reasoning in Open Language ModelsDeepSeekMath 7B improves mathematical reasoning through enhanced data pre-training and Group Relative Policy Optimization, achieving high scores on MATH benchmark without external tools.DeepSeek10.6k citations152 upvotesRead →ReasoningJan 22, 2025DeepSeek-R1: Incentivizing Reasoning Capability in LLMs via Reinforcement LearningReinforcement learning taught a model long step-by-step reasoning on par with OpenAI o1.DeepSeek5,972 citations458 upvotesRead →ReasoningUnverifiedJun 17, 2024DeepSeek-Coder-V2: Breaking the Barrier of Closed-Source Models in Code IntelligenceDeepSeek-Coder-V2, a Mixture-of-Experts language model, excels in code-specific tasks by enhancing coding and mathematical reasoning capabilities while expanding language support and context length.DeepSeek530 citations73 upvotesRead →ReasoningUnverifiedAug 11, 2025MolmoAct: Action Reasoning Models that can Reason in SpaceAction Reasoning Models (ARMs) integrate perception, planning, and control to enable adaptable and explainable robotic behavior, achieving superior performance across various tasks and settings.Ai2232 citations45 upvotesRead →ReasoningUnverifiedJul 22, 2025ThinkAct: Vision-Language-Action Reasoning via Reinforced Visual Latent PlanningThinkAct, a dual-system framework, uses reinforced visual latent planning to enable few-shot adaptation, long-horizon planning, and self-correction in embodied AI tasks by bridging high-level reasoning with low-level action execution.NVIDIA192 citations43 upvotesRead →
About this paper
Venue
Computer Vision and Pattern Recognition
Citations
19, 2 influential · Semantic Scholar
Upvotes
60 · Hugging Face
Lab
UC Berkeley

Changes

CitationsNov 2, 2026Citations rose from 17 to 19.
New summaryOct 26, 2026This paper introduces a task-agnostic mechanism for models to discover and use visual reasoning tokens without explicit supervision.
CitationsOct 12, 2026Citations rose from 15 to 17.
CitationsOct 5, 2026Influential citations rose from 1 to 2.
CitationsOct 5, 2026Citations rose from 10 to 15.
CitationsSep 25, 2026A first count of 1 influential citations.
CitationsSep 25, 2026A first count of 10 citations.
New paperSep 25, 2026Found by the weekly Hugging Face scan; not yet checked by hand.