Benchmarks and evaluation

Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.

12,573 stories · RSS feed

arXiv AI
4d ago

T-LLM Compiler: Trusted LLM-based Code Optimization and Verification Framework

arXiv:2608. 14953v1 Announce Type: new Abstract: Recent advances in Large Language Models (LLMs) have opened opportunities to apply high-level code transformations to the field of code optimization, and it has since emerged as one of the most fundamental tasks for LLMs to perform; however, at present, LLMs struggle to apply wide-ranging code optimization tasks due to both the complexity of the code and the inability to independently verify the correctness of the transformations.

By Zahra Fazel, Sunanda Gamage, Shayan Shirahmad Gale Bagi, Amir H. Ashouri, Tomasz S. Czajkowski, Bryan Chan, Reza Azimi, Yaoqing Gao
arXiv AI
4d ago

Equilibrium Forcing: Adaptive Video Generation Without Noise Conditioning

arXiv:2608. 14706v1 Announce Type: cross Abstract: Standard autoregressive video generation algorithms based on Diffusion and Flow Matching rely on rigid training objectives and static sampling schedules, limiting inference procedures from adapting to the data.

By Hansen Jin Lillemark, Alex Rojas, Zachary Novack, Runqian Wang, Yilun Du, Yian Ma, Taylor Berg-Kirkpatrick, Rose Yu
arXiv AI
4d ago

FloodReasonBench: Benchmarking VLM Reasoning Segmentation for Embodied Flood Response at the Edge

arXiv:2608. 15410v1 Announce Type: cross Abstract: Reasoning segmentation enables vision-language models (VLMs) to translate mission-relevant language requests into pixel-level visual grounding, offering a natural perception interface for embodied agents.

By Rajat Bhattacharjya, Yoomee Jung, Minwoo Kim, Sing-Yao Wu, Eli Bozorgzadeh, Nalini Venkatasubramanian, Nikil Dutt
arXiv AI
4d ago

Bridging the Gap between Labeled and Unlabeled Data via Unified Flow with Feature Memory Bank

arXiv:2608. 16681v1 Announce Type: cross Abstract: Although semi-supervised semantic segmentation ($\text{S}^4$) utilizes abundant unlabeled data to reduce manual labeling burdens, independent training of labeled and unlabeled data causes the former to dominate, which severely degrades pseudo-label quality.

By Shanwen Wang, Xin Sun, Danfeng Hong, Junyu Dong, Patrick Le Callet
arXiv AI
4d ago

ReLoop: Structured Modeling and Behavioral Verification for Reliable LLM-Based Optimization

arXiv:2602. 15983v3 Announce Type: replace-cross Abstract: Large language models (LLMs) can translate natural language into optimization code, but silent failures pose a critical risk: code that executes and returns solver-feasible solutions may encode semantically incorrect formulations---a feasibility--correctness gap reaching 90 percentage points on compositional problems.

By Junbo Jacob Lian, Yujun Sun, Huiling Chen, Chaoyu Zhang, Hanzhang Qin, Chung-Piaw Teo