Recall@1
No mentions found
This entity hasn't been tracked yet, or Iris is still building its knowledge base.
Related Articles from SNS
Major car brand recalls 1,834 motors over ‘electrical fault’
Major car brand recalls 1,834 motors over ‘electrical fault’ Owners are being warned that their cars may burst into flames even while parked, with motorists urged to park the affected vehicles outside and away from buildings Thousands of cars already on British roads have been the subject of a mass recall amid fears they may catch fire, with the same issue impacting a staggering total of 1.3 million vehicles in total worldwide. The fire risk has seen global carmaker Stellantis forced to...
Twins recall former No. 1 pick Lewis from Triple-A...
MINNEAPOLIS -- The Minnesota Twins recalled infielder Royce Lewis from Triple-A St. Paul on Saturday, less than three weeks after the former No. 1 draft pick was sent down to work on his swing mechanics and position flexibility. Lewis, who turned 27 on Friday, was hitting .163 with three home runs and 37 strikeouts in 104 at-bats this season when the Twins demoted him on May 19. In 15 games with St. Paul, he hit .333 with 10 home runs.
Vashu Bhagnani recalls gifting cars after ‘Coolie No 1’ success
Veteran producer Vashu Bhagnani has been in the news for conflict with David Dhawan and Ramesh Taurani surrounding the songs 'Chunari Chunari' and 'Ishq Hona Hai'. Bhagnani has opened up on his long association with Taurani and David. In a detailed statement, Bhagnani said he has largely avoided discussing industry relationships in public, but recent events compelled him to share his perspective after years of what he described as hurt, disappointment and broken trust.
Agreement Metrics for LLM-as-Judge Evaluation: What to Report and Why
arXiv:2606.00093v1 Announce Type: cross Abstract: Validating an LLM judge against human annotations usually means reporting several agreement statistics: accuracy, precision, recall, $F_1$, Cohen's $\kappa$, and one or more rank correlations. A survey of 24 recent LLM-as-judge papers finds metric choice entangled with the judgment scale, tie handling, invalid outputs, and abstention handling, and those choices rarely stated. For binary criteria -- the common case in rubric-based evaluation,...
Superintelligent Retrieval Agent: The Next Frontier of Agentic Retrieval
arXiv:2605.06647v2 Announce Type: replace Abstract: Retrieval-augmented agents are increasingly the interface to large knowledge bases, yet most treat retrieval as a black box: they issue exploratory queries, inspect snippets, and reformulate until evidence emerges. This resembles how a newcomer searches an unfamiliar database rather than how an expert navigates it with strong priors about terminology and likely evidence, causing extra retrieval rounds, latency, and poor recall. We introduce...
Learning Self-Interpretation from Interpretability Artifacts: Training Lightweight Adapters on Vector-Label Pairs
Announce Type: replace Abstract: Self-interpretation methods prompt language models to describe their own internal states, but remain unreliable due to hyperparameter sensitivity. We show that training lightweight adapters on interpretability artifacts, while keeping the LM entirely frozen, yields reliable self-interpretation across tasks and model families. A scalar affine adapter with just $d_\text{model}+1$ parameters suffices: trained adapters generate sparse autoencoder feature labels...
Training-Free Composed Video Retrieval via Visual Representation-Guided Video-LLM Reasoning
arXiv:2606.02321v1 Announce Type: new Abstract: Recent advances in large vision-language models have expanded video retrieval from simple text-based search to more flexible scenarios, where users may specify the desired result through both visual examples and textual instructions. In the CVPR 2026 Reason-Aware Composed Video Retrieval Challenge, the system is required to retrieve a target video according to a reference video and a modification instruction.
Cross-modal linkage risk in clinical vision-language models
arXiv:2606.02276v1 Announce Type: new Abstract: Vision-language models (VLMs) trained on paired chest radiographs and radiology reports learn a shared embedding space that can preserve instance-level image-report correspondence. This poses a privacy risk in settings where radiographs and reports are deliberately kept separate after acquisition, such as image-only data sharing or access-controlled reports, because a de-identified image may be re-linked to its original narrative report through...
A Vision-language Framework for Comparative Reasoning in Radiology
Announce Type: new Abstract: Medical imaging artificial intelligence has achieved strong performance in isolated image interpretation, but remains poorly aligned with radiological practice, where diagnosis and follow-up rely on comparison across prior studies and analogous reference cases. Here we formulate radiological comparison as an entity-aware cross-image reasoning problem and introduce a framework that supports both reference-case retrieval and temporal comparative interpretation. We...
CrossVLA: Cross-Paradigm Post-Training and Inference Optimization for Vision-Language-Action Models
arXiv:2605.21854v2 Announce Type: replace Abstract: Vision-Language-Action (VLA) models have rapidly converged on a small set of architectural patterns: discrete-token autoregression (e.g. OpenVLA) and continuous-action flow-matching (e.g. pi-0.5). Yet preference alignment via Direct Preference Optimisation (DPO) -- the de-facto post-training step in language models -- has been studied almost exclusively on autoregressive VLAs. We present CrossVLA, an empirical study of cross-paradigm VLA...