Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval
Unified multimodal retrieval aims to identify candidates that satisfy complex user intent expressed through heterogeneous inputs. Although Large Vision-Language Model (LVLM)-based retrievers are efficient and scalable, directly encoding raw multimodal inputs often misses fine-grained discriminative cues, leading to confusion among semantically similar candidates. Recent methods mitigate this limitation by generating Chain-of-Thought (CoT) rationales to enrich the query representation. However, s
Record details
Published: 5 August 2026
Source: HuggingFace Daily Papers
Category: Research
Topics: Bias & fairness
Retrieved: 7 August 2026
Related evidence
These records share source-supplied organisations, an exact publisher byline, automatic topics or regions. The reason is shown on every link; related does not mean supporting, agreeing with or verifying this record.
Privileged, but Biased: How PI-Conditioned Teachers Break Self-Distillation
arXiv cs.AI · 5 August 2026
RepoProbe: Benchmarking Architecture-Aware Repository Comprehension with Checklists
arXiv cs.AI · 5 August 2026
IMFACT: Counterfactual Explanations for Time Series via Intrinsic Mode Function Substitution
arXiv cs.AI · 5 August 2026
Local Violation Certification for Linear Predict-Then-Optimize Pipelines
arXiv fairness query · 5 August 2026
Non-asymptotic implicit bias of logistic regression at early-stage gradient descent dynamics
arXiv cs.LG · 5 August 2026
Manipulation-Proof Oblivious Audits against Deceptive Model Providers
arXiv · 5 August 2026
How to cite this record
ethics.ai (5 August 2026), “Learning from Failures: Retrieval-Centric CoT via Hard Negatives for Unified Multimodal Retrieval,” evidence record 17036, https://ethics.ai/record/17036 (originally published by HuggingFace Daily Papers).
Use and limitations
This page is a stable index and citation surface for a source record. ethics.ai did not author the underlying report and has not independently verified every claim. Automatic topics may be imperfect. For consequential use, quote and cite the original publisher.