OmniTrace converts token-level signals into span-level cross-modal attributions for open-ended generation in omni-modal LLMs via generation-time tracing.
Quantifying
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 1
method 1
citation-polarity summary
years
2026 9verdicts
UNVERDICTED 9representative citing papers
Unpack decomposes transformer credit via a unified backward recursion on the φ(S)U template, recovering known IOI circuits with mode labels and showing consistent duplicate-name suppression across Pythia scales from a single forward pass.
Existing visual attribution methods often fail to identify the visual evidence used by LVLMs in chest X-ray reasoning, while MedFocus using unbalanced optimal transport and targeted interventions substantially outperforms them across multiple models and settings.
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
Backward attribution is reframed as integrals over trajectories in a two-player game on the network, unifying gradients and alpha-beta-LRP while enabling new adaptations that outperform prior methods on ViT-B/16 localization metrics.
Personalized soft prompts steer VLM attention to match user-specific gaze patterns, yielding better attention alignment and click prediction in recommendation simulations.
CAAP produces patch attributions in ViTs by direct activation patching on intermediate layers to measure causal contribution to the target class score.
Training a mean-field Transformer under L2 regularization induces an escape from attention-driven token clustering in later layers after initial clustering.
Grad-ECLIP is an equivalent but flawed variant of attention-based interpretation, with two principles proposed to ensure model explanations reflect the original model.
citing papers explorer
-
OmniTrace: A Unified Framework for Generation-Time Attribution in Omni-Modal LLMs
OmniTrace converts token-level signals into span-level cross-modal attributions for open-ended generation in omni-modal LLMs via generation-time tracing.
-
Every Component is a Lookup: Token Attribution and Composition from a Single Decomposition
Unpack decomposes transformer credit via a unified backward recursion on the φ(S)U template, recovering known IOI circuits with mode labels and showing consistent duplicate-name suppression across Pythia scales from a single forward pass.
-
Rethinking Visual Attribution for Chest X-ray Reasoning in Large Vision Language Models
Existing visual attribution methods often fail to identify the visual evidence used by LVLMs in chest X-ray reasoning, while MedFocus using unbalanced optimal transport and targeted interventions substantially outperforms them across multiple models and settings.
-
On What We Can Learn from Low-Resolution Data
Low-resolution data improves high-resolution model performance when high-resolution samples are limited, via KL-divergence bounds and experiments on vision transformers and CNNs.
-
Playing the network backward: A Game Theoretic Attribution Framework
Backward attribution is reframed as integrals over trajectories in a two-player game on the network, unifying gradients and alpha-beta-LRP while enabling new adaptations that outperform prior methods on ViT-B/16 localization metrics.
-
Through Their Eyes: Fixation-aligned Tuning for Personalized User Emulation
Personalized soft prompts steer VLM attention to match user-specific gaze patterns, yielding better attention alignment and click prediction in recommendation simulations.
-
Causal Attribution via Activation Patching
CAAP produces patch attributions in ViTs by direct activation patching on intermediate layers to measure causal contribution to the target class score.
-
Training-Induced Escape from Token Clustering in a Mean-Field Formulation of Transformers
Training a mean-field Transformer under L2 regularization induces an escape from attention-driven token clustering in later layers after initial clustering.
-
Debunking Grad-ECLIP: A Comprehensive Study on Its Incorrectness and Fundamental Principles for Model Interpretation
Grad-ECLIP is an equivalent but flawed variant of attention-based interpretation, with two principles proposed to ensure model explanations reflect the original model.