Qwen3-VL-Seg decodes MLLM bounding boxes into pixel-level referring segmentation via a lightweight box-guided mask decoder, new SA1B-ORS training data, and ORS-Bench evaluation, showing strong open-world performance.
Title resolution pending
4 Pith papers cite this work. Polarity classification is still indexing.
4
Pith papers citing it
verdicts
UNVERDICTED 4representative citing papers
A small set of attention heads carries a 'this statement is wrong' signal that drives sycophancy, factual lying, and instructed lying across models, and survives RLHF and DPO.
LLMs deviate from human moral preferences in kidney allocation scenarios and rarely express indecision, though low-rank fine-tuning with few examples can improve both consistency and uncertainty calibration.
LoVeC uses RL to train LLMs to output verbalized numerical confidence scores for statements in long-form text, achieving better calibration than self-consistency baselines on QA datasets while being 20x faster.
citing papers explorer
-
Qwen3-VL-Seg: Unlocking Open-World Referring Segmentation with Vision-Language Grounding
Qwen3-VL-Seg decodes MLLM bounding boxes into pixel-level referring segmentation via a lightweight box-guided mask decoder, new SA1B-ORS training data, and ORS-Bench evaluation, showing strong open-world performance.
-
LLMs Know They're Wrong and Agree Anyway: The Shared Sycophancy-Lying Circuit
A small set of attention heads carries a 'this statement is wrong' signal that drives sycophancy, factual lying, and instructed lying across models, and survives RLHF and DPO.
-
Who Gets the Kidney? Human-AI Alignment, Indecision, and Moral Values
LLMs deviate from human moral preferences in kidney allocation scenarios and rarely express indecision, though low-rank fine-tuning with few examples can improve both consistency and uncertainty calibration.
-
LoVeC: Reinforcement Learning for Better Verbalized Confidence in Long-Form Generations
LoVeC uses RL to train LLMs to output verbalized numerical confidence scores for statements in long-form text, achieving better calibration than self-consistency baselines on QA datasets while being 20x faster.