T2I-FactualBench is a new three-tier benchmark for factuality of knowledge-intensive concepts in T2I models, using multi-round VQA evaluation to show SOTA models need improvement.
Prism: Self-pruning intrinsic selection method for training-free multimodal data selection.arXiv preprint arXiv:2502.12119
7 Pith papers cite this work. Polarity classification is still indexing.
7
Pith papers citing it
abstract
Visual instruction tuning adapts pre-trained Multimodal Large Language Models (MLLMs) to follow human instructions for real-world applications. However, the rapid growth of these datasets introduces significant redundancy, leading to increased computational costs. Existing methods for selecting instruction data aim to prune this redundancy, but predominantly rely on computationally demanding techniques such as proxy-based inference or training-based metrics. Consequently, the substantial computational costs incurred by these selection processes often exacerbate the very efficiency bottlenecks they are intended to resolve, posing a significant challenge to the scalable and effective tuning of MLLMs. To address this challenge, we first identify a critical, yet previously overlooked, factor: the anisotropy inherent in visual feature distributions. We find that this anisotropy induces a \textit{Global Semantic Drift}, and overlooking this phenomenon is a key factor limiting the efficiency of current data selection methods. Motivated by this insight, we devise \textbf{PRISM}, the first training-free framework for efficient visual instruction selection. PRISM surgically removes the corrupting influence of global background features by modeling the intrinsic visual semantics via implicit re-centering. Empirically, PRISM reduces the end-to-end time for data selection and model tuning to just 30\% of conventional pipelines. More remarkably, it achieves this efficiency while simultaneously enhancing performance, surpassing models fine-tuned on the full dataset across eight multimodal and three language understanding benchmarks, culminating in a 101.7\% relative improvement over the baseline. The code is available for access via \href{https://github.com/bibisbar/PRISM}{this repository}.
citation-role summary
background 4
citation-polarity summary
verdicts
UNVERDICTED 7roles
background 4polarities
background 4representative citing papers
DAS adds a cached per-class bonus derived from noise-conditioned text prompts to cosine scores, improving accuracy by 2.60-5.75 points on UrbanSound8K and mAP by 1.50-1.74 points on FSD50K under urban noise.
INTENT mitigates cross-modal correspondence noise and modality-inherent noise in composed image retrieval via FFT-based visual invariant composition and bi-objective discriminative learning.
HABIT improves robustness in composed image retrieval under noisy triplets by quantifying sample cleanliness via mutual information transition rates and applying dual-consistency progressive learning to retain good patterns and correct bad ones.
ReTrack calibrates directional bias in composed video features using semantic disentanglement and bidirectional evidence alignment to improve retrieval performance on CVR and CIR tasks.
IndusAgent achieves state-of-the-art zero-shot performance on industrial anomaly benchmarks by using a custom Indus-CoT dataset, dynamic tool orchestration, and gated RL to optimize anomaly classification, localization, and reasoning.
TCAP detects backdoor samples in MLLM fine-tuning via tri-component attention profiling, GMM-based head identification, and EM vote aggregation.
citing papers explorer
-
T2I-FactualBench: Benchmarking the Factuality of Text-to-Image Models with Knowledge-Intensive Concepts
T2I-FactualBench is a new three-tier benchmark for factuality of knowledge-intensive concepts in T2I models, using multi-round VQA evaluation to show SOTA models need improvement.
-
Drift-Augmented Scoring: Text-Derived Noise Robustness for Zero-Shot Audio-Language Classification
DAS adds a cached per-class bonus derived from noise-conditioned text prompts to cosine scores, improving accuracy by 2.60-5.75 points on UrbanSound8K and mAP by 1.50-1.74 points on FSD50K under urban noise.
-
INTENT: Invariance and Discrimination-aware Noise Mitigation for Robust Composed Image Retrieval
INTENT mitigates cross-modal correspondence noise and modality-inherent noise in composed image retrieval via FFT-based visual invariant composition and bi-objective discriminative learning.
-
HABIT: Chrono-Synergia Robust Progressive Learning Framework for Composed Image Retrieval
HABIT improves robustness in composed image retrieval under noisy triplets by quantifying sample cleanliness via mutual information transition rates and applying dual-consistency progressive learning to retain good patterns and correct bad ones.
-
ReTrack: Evidence-Driven Dual-Stream Directional Anchor Calibration Network for Composed Video Retrieval
ReTrack calibrates directional bias in composed video features using semantic disentanglement and bidirectional evidence alignment to improve retrieval performance on CVR and CIR tasks.
-
IndusAgent: Reinforcing Open-Vocabulary Industrial Anomaly Detection with Agentic Tools
IndusAgent achieves state-of-the-art zero-shot performance on industrial anomaly benchmarks by using a custom Indus-CoT dataset, dynamic tool orchestration, and gated RL to optimize anomaly classification, localization, and reasoning.
-
TCAP: Tri-Component Attention Profiling for Unsupervised Backdoor Detection in MLLM Fine-Tuning
TCAP detects backdoor samples in MLLM fine-tuning via tri-component attention profiling, GMM-based head identification, and EM vote aggregation.