TEMA is the first framework for multi-modification composed image retrieval, using entity mapping to improve accuracy on both new complex datasets and existing benchmarks while balancing efficiency.
hub Canonical reference
Delving deeper: Hierarchi- cal visual perception for robust video-text retrieval
Canonical reference. 80% of citing Pith papers cite this work as background.
13
Pith papers citing it
Background
80% of classified citations
hub tools
citation-role summary
background 5
citation-polarity summary
years
2026 13roles
background 5representative citing papers
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.
OCL is a governance layer for LLM agents that cuts unsafe executions from 88% to near-zero and raises valid success from 12% to 96% in adversarial buyer-seller negotiations across frontier LLMs.
TOPD improves on-policy distillation for LLM reasoning by using near-future guidance to identify divergent states, raising average accuracy from 47.8% to 52.2% on math benchmarks including AIME24 and AIME25.
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.
Air-Know decouples MLLM-based external arbitration from proxy learning via knowledge internalization and dual-stream training to overcome noisy triplet correspondence in 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 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.
ROGLE introduces automated pseudo region-sentence pairs via RSM and multi-granular learning to boost fine-grained alignment in text-based person search, plus the P-VLG benchmark with over 100k annotated regions.
VOTE-RAG applies retrieval voting across diverse queries and response voting across independent generations to mitigate hallucination-on-hallucination in RAG, matching or exceeding complex baselines on six benchmarks with a parallelizable design.
A study deriving mathematical formulations and bounds for diffusion editing objectives while empirically comparing methods on fidelity and control metrics and discussing ethical issues.