…From Token Efficiency to Oversight Evasion Published on May 29 Submitted by Federico Torrielli on Jun 1 AI Safety & Interpretability Lab Authors: , William Brach , Federico Torrielli , , , , , Lukas Galke Poech Abstract Research examines…
…Staged Post-Training with Visually Debiased Evaluation Published on May 13 Submitted by liu on May 15 StepFun Authors: , , , , , , Abstract Research demonstrates that current omni-modal benchmarks may inflate performance through visual…
…While modern Arabic speakers continue to value poetry, existing research on Arabic poetry within Large Language Models (LLMs) has primarily focused on analysis tasks such as interpretation or metadata prediction, e.g…
…Seojeong Park , Jiho Choi , , , , Abstract Researchers identify a perceptual judgment bias in multimodal large language models where visual evidence is overlooked for textual plausibility, and propose a training framework using a perturbed…
…Reversing Teacher Signals for Reasoning Exploration with Self-Distilled RLVR Published on May 11 Submitted by JeonghyeKim on May 12 Microsoft Research Authors: , , , Abstract RLRT enhances self-distillation by reinforcing successful student…
…Extensive experiments and analyses demonstrate that ATLAS achieves superior performance on challenging benchmarks while maintaining clear interpretability. We hope ATLAS offers a new paradigm inspiring future visual reasoning research. View arXiv page…
…Kirscher , , , , , , , , , , , , , , , , , Abstract Researchers developed a new dataset and challenge for pancreatic cancer staging that emphasizes uncertainty-aware AI models capable of handling ambiguous tumor-vessel interfaces, revealing that traditional segmentation metrics fail…
…Extensive experiments on chest X-ray interpretation demonstrate that our 7B model achieves superior robustness, outperforming even proprietary source models in average accuracy. Furthermore, we release CXR-MAX, a large-scale benchmark…
…Venkata Pushpak Teja Menta Abstract Researchers enhance a non-Indic-native text-to-speech system by implementing a Brahmic Unified Phoneme Space, LoRA adaptation, and voice-prompt recovery techniques to achieve commercial…
…Foundation segmentation models such as the SAM series produce high-quality masks, but they rely on low-level visual prompts and cannot natively interpret complex conversational instructions. Existing segmentation MLLMs narrow this…
To show you the most relevant results, we’ve omitted some entries very similar to those already shown. Repeat the search with the omitted results included.