conftrace_

information flow

49 papers

Explore in graph

Co-occurring keywords

attention mechanism (4001) model compression (3302) large language model (13587) neural network (6616) multimodal learning (4645) representation learning (6206) token representation (45) graph neural network (3962) mechanistic interpretability (133) recurrent neural network (1790)

Papers

LLMs Faithfully and Iteratively Compute Answers During CoT: A Systematic Analysis With Multi-step Arithmetics EACL 2026
Reasoning Fails Where Step Flow Breaks ACL 2026
FG-TRACER: Tracing Information Flow in Multimodal Large Language Models in Free-Form Generation WACV 2026
Follow the Flow: On Information Flow Across Textual Tokens in Text-to-Image Models ACL 2026
Detecting LLM Hallucination Through Layer-wise Information Deficiency: Analysis of Ambiguous Prompts and Unanswerable Questions EMNLP 2025
SHIFT: Smoothing Hallucinations by Information Flow Tuning for Multimodal Large Language Models ICCV 2025
Fact Recall, Heuristics or Pure Guesswork? Precise Interpretations of Language Models for Fact Completion ACL 2025
InDistill: Information Flow-Preserving Knowledge Distillation for Model Compression WACV 2025
VITAL: More Understandable Feature Visualization through Distribution Alignment and Relevant Information Flow ICCV 2025
On Oversquashing in Graph Neural Networks Through the Lens of Dynamical Systems AAAI 2025
From Redundancy to Relevance: Information Flow in LVLMs Across Reasoning Tasks NAACL 2025
Value Residual Learning ACL 2025
Mamba Knockout for Unraveling Factual Information Flow ACL 2025
Mitigating Hallucination in Large Vision-Language Models through Aligning Attention Distribution to Information Flow EMNLP 2025
Cross-modal Information Flow in Multimodal Large Language Models CVPR 2025
GNNavi: Navigating the Information Flow in Large Language Models by Graph Neural Network ACL 2024
SparseFlow: Accelerating Transformers by Sparsifying Information Flows ACL 2024
Increasing Biases Can Be More Efficient Than Increasing Weights WACV 2024
DenseFormer: Enhancing Information Flow in Transformers via Depth Weighted Averaging NIPS 2024
An Information-Flow Perspective on Algorithmic Fairness AAAI 2024
Unlocking the Future: Exploring Look-Ahead Planning Mechanistic Interpretability in Large Language Models EMNLP 2024
Initialization is Critical to Whether Transformers Fit Composite Functions by Reasoning or Memorizing NIPS 2024
Information Flow Routes: Automatically Interpreting Language Models at Scale EMNLP 2024
Layer Collaboration in the Forward-Forward Algorithm AAAI 2024
Test Coverage for Network Configurations NSDI 2023