AI Chronicles

text-generation · 3192 likes · 159967 downloads

text-generation · 2556 likes · 597090 downloads

image-text-to-text · 1600 likes · 630246 downloads

image-text-to-text · 1184 likes · 1113871 downloads

text-generation · 5130 likes · 1168364 downloads

text-generation · 929 likes · 288741 downloads

text-generation · 623 likes · 233701 downloads

text-generation · 623 likes · 114499 downloads

text-generation · 760 likes · 72715 downloads

text-to-video · 1836 likes · 716922 downloads

text-generation · 499 likes · 34371 downloads

image-text-to-text · 2384 likes · 3055962 downloads

image-text-to-text · 2299 likes · 5714598 downloads

text-generation · 490 likes · 212201 downloads

image-text-to-text · 1864 likes · 5177216 downloads

text-generation · 376 likes · 191409 downloads

text-to-image · 441 likes · 56953 downloads

text-generation · 1671 likes · 1935113 downloads

text-to-speech · 585 likes · 108614 downloads

text-generation · 283 likes · 7629 downloads

text-generation · 336 likes · 46677 downloads

image-text-to-text · 917 likes · 920157 downloads

automatic-speech-recognition · 756 likes · 107111 downloads

text-generation · 296 likes · 135452 downloads

image-text-to-text · 3119 likes · 11203982 downloads

text-to-image · 264 likes · 39515 downloads

text-generation · 412 likes · 5769728 downloads

text-generation · 181 likes · 2671 downloads

text-generation · 200 likes · 136933 downloads

225 likes · 10 downloads

text-generation · 183 likes · 21935 downloads

text-generation · 191 likes · 5792 downloads

text-generation · 154 likes · 511 downloads

image-text-to-text · 2554 likes · 896058 downloads

150 likes · 0 downloads

tabular-classification · 89 likes · 3 downloads

text-generation · 120 likes · 901 downloads

image-to-video · 138 likes · 0 downloads

text-generation · 127 likes · 13038 downloads

text-generation · 130 likes · 196441 downloads

image-text-to-text · 107 likes · 12635 downloads

text-generation · 138 likes · 1766 downloads

token-classification · 96 likes · 414 downloads

102 likes · 0 downloads

image-to-video · 1506 likes · 1791425 downloads

text-generation · 63 likes · 38140 downloads

text-generation · 53 likes · 33018 downloads

text-generation · 56 likes · 37885 downloads

image-to-image · 49 likes · 0 downloads

text-generation · 49 likes · 16824 downloads

270 likes · 0 downloads

46 likes · 20 downloads

113 likes · 3377 downloads

text-generation · 54 likes · 15415 downloads

text-generation · 92 likes · 7628 downloads

image-text-to-text · 125 likes · 443 downloads

Vein recognition is a secure biometric technology often constrained by limited annotated data and imaging variations. While data augmentation mitigates this, strategies designed for natural images may disrupt the fine-grained topology and textures essential for identity discrimination. We present AGVBench, which evaluates 30 representative augmentation strategies on five public palm- and finger-vein datasets with seven backbone architectures, covering classic CNNs, vision transformers, and vein-specific recognition models. Our results show that multi-image mixing methods (e.g., MixUp, PuzzleMix, StarMixup) generally provide the strongest recognition performance. However, they are often poorly calibrated and vulnerable to adversarial perturbations, revealing a clear inconsistency between clean accuracy and adversarial security. We also find that severe geometric transformations frequently degrade recognition, which is potentially due to feature misalignment or spatial cropping, and that augmentation effectiveness varies across palm and finger vein datasets. These findings prove that accuracy-centric evaluation is insufficient for biometric augmentation. AGVBench provides standardized protocols to support reproducible research and guide the design of reliable, secure, and robust vein recognition systems. Our codebase is available at https://github.com/Advance-VeinTech-Innovators/AGVBench.

Skills are becoming a reusable operational layer for LLM agents, encoding SOPs, domain rules, tool workflows, scripts, and validation routines. In realistic skill repositories, overlapping skills make reliable skill-use difficult. Final verifier success is too coarse for both evaluation and training, since an agent may pass through trial and error while selecting distractor skills, skipping required steps, composing workflows incorrectly or omitting final checks. We introduce SkillCoach, a self-evolving rubric framework for evaluating and enhancing agentic skill-use. SkillCoach derives skill-grounded process rubrics from real rollouts and evaluates trajectories along four dimensions: skill selection, skill following, skill composition, and skill-grounded reflection. It keeps the external verifier as a separate outcome signal, allowing process quality to be distinguished from accidental task success. The evolved rubrics further serve as process supervision for selecting high-quality training trajectories. Experiments show that evolved rubrics substantially improve evaluation quality, expose failures hidden by final accuracy, and provide stronger supervision signals than outcome-only filtering for enhancing agentic skill-use.

Evaluating LLM agents on benchmarks like SWE-Bench and GAIA can be expensive, time-consuming, and requires complex infrastructure. A single evaluation can cost thousands of dollars and take days to complete. In contrast, non-agentic LLM benchmarks that test individual capabilities (e.g., reasoning, code generation) are fast and cheap to run. In this paper, we investigate whether performance on expensive agentic benchmarks can be accurately predicted by the performance on a small, carefully selected subset of atomic evaluation instances. We introduce PACE, a framework that constructs proxy benchmarks by selecting instances from existing non-agentic evaluations whose aggregate scores most reliably predict model performances on agentic benchmarks. Given a pool of candidate instances spanning atomic capabilities, PACE fits a regression that maps a model's scores on a compact subset of source instances to its score on the target agentic benchmark. The subset itself is curated by combining two complementary instance-selection strategies, target-relevance local selection and globally informative global selection. We apply PACE to the 4 target agentic benchmarks in this paper, which yields PACE-Bench, the concrete proxy benchmark that we evaluate in the paper. Experiments across 14 models, 4 agentic benchmarks, and 19 non-agentic benchmarks show that PACE-Bench predicts agentic scores with leave-one-out cross-validation (LOOCV) mean absolute error (MAE) under 4%, Spearman correlation above 0.80, and pairwise model-ranking accuracy around 85%, all at much less than 1% of the full agentic evaluation cost. We further analyze the selected proxy instances, revealing which skills each agentic benchmark uniquely demands. PACE enables practitioners to obtain reliable estimates of agentic performance during model development, selection, and routing, without the overhead of full agent evaluation.

Autonomous agents are increasingly expected to improve executable policies through feedback, yet existing evaluations often collapse this process into a final score or confound it with open-ended software-engineering progress. We introduce Autonomous Policy Evolution, a controlled evaluation setting in which a harness-model agent repeatedly edits an executable policy system under a fixed interaction budget. We instantiate this setting in EvoPolicyGym, a benchmark built from compact interactive RL environments that evaluates how agents iteratively improve explored policies. On the EvoPolicyGym suite, GPT-5.5 achieves the strongest aggregate rank score and top-two performance on all 16 environments. Beyond leaderboard results, EvoPolicyGym also provides trajectory-level diagnostics that distinguish how agents allocate budget, convert feedback into parametric tuning. These analyses show that strong autonomous policy evolution depends not only on isolated task wins, but on discovering task-appropriate mechanisms and refining policies under bounded feedback.