ConeSep tackles noisy triplet correspondences in composed image retrieval by introducing geometric fidelity quantization to locate noise, negative boundary learning for semantic opposites, and targeted unlearning via optimal transport, outperforming prior methods on FashionIQ and CIRR.
Canonical reference
AutoNeural: Co-Designing Vision-Language Models for NPU Inference
Canonical reference. 100% of citing Pith papers cite this work as background.
11
Pith papers citing it
Background
100% of classified citations
citation-role summary
background 5
citation-polarity summary
years
2026 11roles
background 5polarities
background 5representative citing papers
First end-to-end RAG on mobile NPU delivers 18.1x faster prefilling, 4x lower latency and energy than CPU on Snapdragon X Elite with equivalent quality.
Rock Tokens in on-policy distillation persist at high loss, account for up to 18% of outputs, absorb large gradient norms, but add negligible value to reasoning performance.
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.
Introduces DCD, a wavelet-based stage-wise distillation technique that preserves structural details in efficient 3D multi-modal MRI segmentation models.
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.
FAST uses a Temporal-Spatial-Temporal structure with attention and Mamba modules plus learnable embeddings to achieve better accuracy on traffic prediction tasks than previous models.
Neural reranking in a hybrid RAG system raises high-quality answer rates from 33.5% to 49.0% on financial report questions.
citing papers explorer
-
ConeSep: Cone-based Robust Noise-Unlearning Compositional Network for Composed Image Retrieval
ConeSep tackles noisy triplet correspondences in composed image retrieval by introducing geometric fidelity quantization to locate noise, negative boundary learning for semantic opposites, and targeted unlearning via optimal transport, outperforming prior methods on FashionIQ and CIRR.
-
Energy-Efficient On-Device RAG on a Mobile NPU: System Design and Benchmark on Snapdragon X Elite
First end-to-end RAG on mobile NPU delivers 18.1x faster prefilling, 4x lower latency and energy than CPU on Snapdragon X Elite with equivalent quality.
-
Cornerstones or Stumbling Blocks? Deciphering the Rock Tokens in On-Policy Distillation
Rock Tokens in on-policy distillation persist at high loss, account for up to 18% of outputs, absorb large gradient norms, but add negligible value to reasoning performance.
-
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.
-
Detail Consistent Stage-Wise Distillation for Efficient 3D MRI Segmentation
Introduces DCD, a wavelet-based stage-wise distillation technique that preserves structural details in efficient 3D multi-modal MRI segmentation models.
-
MedSynapse-V: Bridging Visual Perception and Clinical Intuition via Latent Memory Evolution
MedSynapse-V proposes a latent memory evolution framework with meta-query prior retrieval, causal counterfactual refinement via RL, and intrinsic memory transition to improve diagnostic accuracy over chain-of-thought baselines in medical VLMs.
-
FAST: A Synergistic Framework of Attention and State-space Models for Spatiotemporal Traffic Prediction
FAST uses a Temporal-Spatial-Temporal structure with attention and Mamba modules plus learnable embeddings to achieve better accuracy on traffic prediction tasks than previous models.
-
Enhancing Financial Report Question-Answering: A Retrieval-Augmented Generation System with Reranking Analysis
Neural reranking in a hybrid RAG system raises high-quality answer rates from 33.5% to 49.0% on financial report questions.
- Seeing is Coding: On the Effectiveness of Vision Language Models in Code Understanding