train of thought
PulseAugur coverage of train of thought — every cluster mentioning train of thought across labs, papers, and developer communities, ranked by signal.
- instance of Chain Of Thought 90%
- instance of Tree of Thoughts: Deliberate Problem Solving with Large Language Models 90%
- instance of alphaXiv 90%
- used by Chain Of Thought 70%
- used by CatalyzeX 70%
- instance of Gotit.pub 70%
- used by Group Relative Policy Optimization 70%
- used by zero-shot learning 70%
- instance of ScienceCast 70%
- used by Few-shot learning 70%
- used by Tree of Thoughts: Deliberate Problem Solving with Large Language Models 70%
16 day(s) with sentiment data
-
Research questions effectiveness of CoT training in LLM agents
A new research paper investigates the effectiveness of Chain-of-Thought (CoT) training in large language model (LLM) agents. The study compares "prompt actions" (predicting actions without CoT) against "CoT actions" (pr…
-
New benchmarks push video AI to ground answers in temporal evidence · 4 sources tracked
Two new research papers introduce benchmarks and models for video question answering that focus on temporal reasoning and evidence grounding. The EG-VQA benchmark, with over 11,000 QA pairs and temporal evidence annotat…
-
New research reveals comparative LLM bias evaluations amplify discrimination
A new research paper published on arXiv addresses the critical issue of evaluating social biases in large language models (LLMs). The study highlights significant methodological fragmentation in current research, leadin…
-
PointVG-R model enhances visual grounding with geometric reasoning · 3 sources tracked
Researchers have developed PointVG-R, a novel reasoning-guided Multi-modal Large Language Model (MLLM) designed to improve precise pointing localization in images. This model integrates geometric-aware reasoning, Reinfo…
-
Neuro-Symbolic Drive enhances driving VLAs with rule-grounded reasoning
Researchers have developed Neuro-Symbolic Drive, a novel framework that enhances the reasoning capabilities of driving Visual Language Models (VLAs). This approach integrates classical rule-based planning logic with the…
-
SPIRAL framework enhances language model reasoning with parallel and aggregated traces
Researchers have developed SPIRAL, a new framework designed to enhance language model reasoning capabilities by integrating sequential, parallel, and aggregation methods. Unlike traditional models optimized solely for s…
-
New framework visualizes and audits complex AI reasoning chains
Researchers have developed ReasoningLens, an open-source framework aimed at improving the transparency and auditability of large reasoning models. This framework structures complex reasoning chains into interactive hier…
-
Claude Language Model: Techniques for Enhanced Output
This article explores three techniques for improving output from the Claude language model: Chain of Thought, Few-Shot learning, and Zero-Shot learning. It aims to guide users on how to achieve better results by employi…
-
Anthropic's Claude AI: Techniques, Comparisons, and Business Applications
Several articles discuss techniques and applications for Anthropic's Claude AI. Authors explore methods to enhance Claude's output, such as "Claude Prompt vs Claude Looping" and "Chain of Thought, Few-Shot, Zero-Shot" p…
-
VideoLatent MLLM enhances video reasoning with efficient latent self-forcing
Researchers have developed VideoLatent, a new multimodal large language model (MLLM) designed for enhanced video understanding and reasoning. Unlike previous methods that required extensive annotations or incurred high …
-
Edge AI accuracy boosted with IoT data preprocessing for LLMs
Researchers have developed a prompt-side preprocessing framework to enhance the accuracy of local large language models (LLMs) for Internet of Things (IoT) sensor data analysis. This method transforms raw sensor reading…
-
Reasoning AI models show limited ability to detect changes in their thought processes
A new study published on arXiv investigates the ability of reasoning models to detect modifications made to their chains of thought (CoT). Researchers found that these models exhibit only modest accuracy in identifying …
-
New research explores interactive visualization and causal attribution for LLM reasoning
Researchers are exploring new methods to enhance the interpretability and reliability of large language models (LLMs) through chain-of-thought (CoT) reasoning. One approach, Vis-CoT, transforms linear CoT text into inte…
-
New study evaluates LLM lie detectors, finding limitations in trained deception
Researchers have developed and evaluated lie detectors for large language models, finding that while these detectors show promise, their effectiveness is limited, particularly when models are trained to be deceptive. Th…
-
New framework ThinkDeception enhances multimodal deception detection with interpretable AI
Researchers have introduced ThinkDeception, a new framework for multimodal deception detection that utilizes reinforcement learning and large language models. This approach aims to overcome the interpretability limitati…
-
New research enables editable and composable KV cache for LLMs
A new research paper introduces a novel method for optimizing KV cache usage in large language models, enabling editable and composable notes within the prefill stage. This approach allows for efficient editing of model…
-
New framework enhances multimodal math reasoning with dependency-guided training
Researchers have developed MathVis-Fine, a new framework designed to improve multimodal mathematical reasoning by better aligning visual supervision with necessity. The approach addresses limitations in current methods …
-
New framework internalizes Chain-of-Thought for universal image restoration
Researchers have developed CoTIR, a novel framework for universal image restoration that integrates Chain-of-Thought (CoT) reasoning directly into a single model. This approach aims to overcome the limitations of tradit…
-
New MIRAGE benchmark reveals amplified anti-Muslim bias in LLMs
A new benchmark called MIRAGE has been developed to assess anti-Muslim bias in large language models, moving beyond simple prompt completion to evaluate reasoning, agentic decision-making, and time-coupled conditions. T…
-
Research confirms tree-style branching is key for AI thought advantage estimation
A new research paper explores the effectiveness of tree-style branching in Group Relative Policy Optimization (GRPO), a method for training Chain-of-Thought reasoning in AI models. The study, utilizing the multivariate …