Papers with Claude-4.5
From Imitation to Discrimination: Progressive Curriculum Learning for Robust Web Navigation (2026.findings-acl)
Copied to clipboard
| Challenge: | Text-based web agents offer computational efficiency for autonomous web navigation, yet they lack discrimination capabilities to reject plausible but incorrect elements in densely populated pages. |
| Approach: | They propose a model that uses a text-based web agent to learn to discriminate against incorrect elements in densely populated HTML and a training curriculum to synthesize diverse cross-domain tasks with strict verification. |
| Outcome: | Empirical evaluation shows that the model performs better than open-source models with 58.7% step success rate. |
Into the Gray Zone: Domain Contexts Can Blur LLM Safety Boundaries (2026.acl-long)
Copied to clipboard
Ki Sen Hung, Xi Yang, Chang Liu, Haoran Li, Kejiang Chen, Changxuan Fan, Tsun On Kwok, Weiming Zhang, Xiaomeng Li, Yangqiu Song
| Challenge: | a goal of LLM alignment is to balance usefulness with harmlessness, but this conflictes when knowledge serves both legitimate and malicious purposes. |
| Approach: | They propose a framework that combines safety-research contexts with adversarial interactions to exploit a vulnerability in Jargon queries. |
| Outcome: | a framework outperforms existing methods in analyzing Jargon queries, a study shows . it achieves 93% of attacks across seven models, while remaining useful, the authors say . |
CASS: Nvidia to AMD Transpilation with Data, Models, and Benchmark (2026.acl-long)
Copied to clipboard
Ahmed Heakl, Gustavo Bertolo Stahl, Sarim Hashmi, Seung Hun Eddie Han, Mukul Ranjan, Arina Kharlamova, Salman Khan, Abdulrahman Mahmoud
| Challenge: | Cross-architecture GPU code translation is essential for unlocking low-level hardware portability, yet no scalable solution exists. |
| Approach: | They propose a dataset and model suite for source- and assembly-level GPU code translation that trains domain-specific translation models that achieve 88.2% accuracy on CUDA HIP and 69.1% on SASS RDNA3 . |
| Outcome: | The proposed model achieves 88.2% accuracy on CUDA HIP and 69.1% on SASS RDNA3 outperforming commercial baselines including GPT-5.1, Claude-4.5, and Hipify by wide margins. |