Tag: #v1120 results
Introduces Silence Routing framework for collective intelligence in taste domains using music preferences. Specifies when contributors should speak, report, or stay silent. Simulation shows accuracy gains over baselines only when silence is allowed.
Adapts SigLIP contrastive learning with a Jaccard-based sigmoid loss for multi-label ECG classification using real-world data. Incorporates medical knowledge and techniques like higher embedding dimensions and random cropping. Per-label analysis identifies prediction challenges across ECG findings.
Explores semantic labeling for TPRA questionnaires using LLMs and hybrid SSSL. Compares direct labeling vs. clustering and propagation. Improves retrieval when labels are discriminative.
Proposes no-reference IQA for real-world super-resolved images using content-free SSL. Pretrains multi-SR model representations via contrastive learning. Includes new SRMORSS dataset for pretext training.
Introduces ScratchWorld benchmark with 83 tasks for multimodal GUI agents in Scratch. Uses primitive/composite modes and execution-based evaluation. Exposes reasoning-acting gaps in state-of-the-art agents.
OmniSteer addresses cross-modality vulnerabilities in OLLMs using AdvBench-Omni dataset and modality-semantics decoupling. Uncovers mid-layer dissolution and extracts golden refusal vector via SVD. Boosts refusal rate to 91.2% while preserving capabilities.
Introduces first reproducible ECoG dataset from rat models for Parkinson's disease prediction. Swap-Adversarial Framework (SAF) uses channel swapping and domain-adversarial training to tackle inter-subject variability and HDLSS issues. Outperforms baselines in cross-subject, cross-session, and cross-dataset settings, generalizing to EEG.
RSHallu studies hallucinations in remote-sensing MLLMs with a new taxonomy, benchmark, and dual-mode checker. Provides datasets for mitigation via training and plug-and-play strategies. Improves hallucination-free rates by up to 21% on RS tasks.
DRPO tackles model collapse in off-policy generative recommendation via optimistic distributionally robust optimization. Proves hard filtering recovers high-quality data from noisy logs. Achieves SOTA on mixed-quality benchmarks.
RLCER reinforces chain-of-thought via self-evolving rubrics without human labels. Outperforms outcome-centric RLVR on reasoning tasks. Rubrics boost inference as prompts.