127,473Total entries

60Added by human

127,413Found by agent

13Categories

Knowledge catalogue

Search: “concepts”

3,866 results

Tutorials

Distilling Visual Reasoning into Text Space

DGX agent

arXiv:2609.34408v1 Announce Type: new Abstract: Large Vision-Language Models (LVLMs) have shown strong promise for multimodal reasoning, yet often struggle with tasks requiring concepts beyond what is

tutorialsarxiv-cs-cv

29 Sept 2026

Local Ai

Do World Models Learn Global Understanding?

DGX agent

arXiv:2609.34058v1 Announce Type: new Abstract: AI systems often feel brittle and fragmented. A large language model (LLM) may correctly explain a concept but fail to apply it, or follow safety instru

Search: “concepts”

Distilling Visual Reasoning into Text Space

Do World Models Learn Global Understanding?

Domain-Adapted Diffusion Models for Conditional Independence Testing

Generative Uncertainty as a Self-supervised Signal for Semantic Similarity Learning

Verifying the Linear Representation Hypothesis: How Interpretable Are Vision SAEs?

Autoheal raises $7.9M to evaluate and fix AI agents with… AI agents

FeatMark: Feature-level Watermark Protection against Mimicry Attacks with Diffusion Models

LandscapeSHAP: Which Persistent Homology Class Gets the Credit?

Qwen3.8-Flash-Next 177B NVFP4(119GiB): SSD streaming at 9-10 tok/s on one 16 GB RTX 5060 Ti + 32 GB RAM

CodeGraph: Open-Taxonomy Knowledge Graph for Source Code with Wikidata Grounding

Foundations of Large Language Models

Beyond Mean Foils: Auditing Worst-Foil Specificity in Frozen CLIP Region Explanations

Hidden not Deleted: How Networks Suppress Entangled Features

Read-Best Is Not Steer-Best: A Probing--Steering Layer Dissociation in Omni-Modal Large Language Models

Replicating the Geometry of Emotion Representations in a Base Open-Weights Model

Efficient Unified Multimodal Understanding (EUMU): Winning Solution for the MUMU Track at the 8th LSVOS Challenge

Quantifying Mechanical Intelligence in Legged Robots with Information Theory

Decodability is Not Causality: Dissociating Probe Readouts from Behavioral Drivers via SAE Decomposition

DR.WILSS: Diffusion-Based Replay for Weakly Supervised Continual Semantic Segmentation

Efficient Robust Learning at the Information-Theoretic Limit

RLLBC-Lib: An Educational Code Library for Reinforcement Learning and Learning-Based Control

Adaptive Bayesian Partner Selection for Federated Clinical Centers

Execution Flexibility in Automated Planning: A Comparative Evaluation of Deordering and Reordering Strategies

SciNLP: A Domain-Specific Benchmark for Full-Text Scientific Entity and Relation Extraction in NLP

AlgoRAG: Retrieval-Augmented Generation for Theoretical Computer Science Education -- A Comprehensive Evaluation Framework for Algorithm Analysis and Complexity Theory

ProIQA: A Process-Based Framework for Fine-Grained Math Item Quality Assessment

SALUTE: Benchmarking and Adapting LLMs for the Defense Domain

Automated Detection and Structuring of Social Tipping Point Evidence in Climate related Documents: A Modular AI Framework

Beyond ID Embeddings: Process-Grounded Language Modeling for Cognitive Diagnosis

Images do not properly generate in ComfyUI + Krea2

Satisficing Regret Minimization in Bandits: Constant Rate and Light-Tailed Distribution

Space as an Interventional Invariant: Cross-Modal Predictive Geometry for Stratified Cities and Em-Spaced Intelligence

Label Differential Privacy via Aggregation

CircuTutor: Transforming Static Circuit Problems into Intelligent and Dynamic Tutoring

High-probability guarantees for linear accessibility in feature superposition

Modus Tollens and Counterfactuals and Counterfactual Reasoning Based on Three Types of Negation

Spillover-Aware Multi-Value Steering for Pluralistic LLM Alignment

Thermodynamic Cyclic Processes with Markov Samplers in Bayesian Inference

An overview of 3D Vision-Language Models

I made a short explanation of KV Cache — is this understandable for beginners?

Linear Algebra Foundations of Efficient Attention: A Phase Reversal in Rank Collapse Under SVD Compression

Observability conditions for neural state-space models with eigenvalues and their roots of unity

SAEScientist-Bench: Can AI Agents Conduct Autonomous SAE Interpretability Research?

Do LLMs Exhibit Coherent Knowledge Structures in Mathematical Reasoning? A Perspective from Knowledge Space Theory

From Interpretability Methods to Interpretable Models

CORE: Improving Compositional Reasoning in MLLM Embedding via Reranker Distillation

FoRIS: Progressive Foreground Refinement for Training-Free In-Context Segmentation

From Deceptive Outputs to Deceptive Mechanisms: A Causal Framework for Language-Model Deception Research