The Archive

PaperGym creates training environments from research papers using rubrics as reward signals for AI research-plan generation.

Controlled study of 13 LLM scales (Qwen, GPT) on ontology learning tasks shows mixed effects of model size on performance.

Quantum generative models face generalization gaps when trained classically and deployed on quantum hardware.

ASPIRE benchmark evaluates LLM self-evolution from vague natural-language goals without predefined metrics.

Stress-testing shows efficient responsible-AI evaluation (quantization, batching) can change benchmark conclusions on bias and fairness.

BLOOM-WILT uses logit tilting to efficiently elicit rare behaviors in deployed LLMs without model training.

Industrial perspective on post-training as maintenance: managing dataware mixture updates within fixed budgets without regression.

S³Gym benchmark evaluates LLM agent self-improvement through coupled self-testing, self-judging, and learning from experience.

Multimodal learning for grapevine cold hardiness prediction via transfer learning across regions.

Task-conditioned adapter for class-incremental learning balances parameter efficiency with per-task representation quality.

Theoretical analysis of minimax loss in recursive discrete distribution estimation under watermarking, contrasting oracle-assisted and unassisted settings.

Method to recover multi-token concept vectors directly from J-lens LLM interpretability tool without fine-tuning, using first-token cues.

Framework for reducing token consumption in LLM agents reasoning over unstructured data via adaptive pre-structuring, addressing enterprise AI cost barriers.

Analysis showing sycophantic agreement emerges unintentionally from contrastive preference optimization; demonstrates transfer across model families via OLMo 3.

Framework reconciling process supervision with outcome-based credit assignment in agentic RL using privileged information, improving fine-grained policy learning.

AutoSciRub framework for autonomous research agents using automatic rubric induction to define task-specific success criteria before task execution.

Study of scaling large reasoning models beyond human supervision using verifiable rewards, examining paths toward agentic reasoning without direct human oversight.

Lightweight two-stage real-time video anomaly detection using YOLO pose estimation and CLIP semantic similarity scoring on skeletal keypoints.

Soft Latent Thinking method enabling LLM reasoning in continuous embedding space instead of discrete tokens, reducing per-step compute while improving pass@k.

Analysis revealing hidden-state probes decode correct reasoning answers when native LLM sequence scoring fails, suggesting output bottleneck vs. capability gap.

Transformer parameterization with 280 parameters achieves perfect length generalization on Boolean algebra circuits via depth-1 reduction.

Model-internal token saliency via residual stream analysis compresses chain-of-thought reasoning while preserving model performance.

Theoretical analysis of when text embeddings preserve latent topic mixtures for clustering and causal inference tasks.

Learned query generation (LoQ, FeedQ) improves information extraction by 18.6 F1-points, outperforming model scaling across clinical benchmarks.

Analysis of heterogeneous working memory in coding agents reveals distinct retention profiles for instructions, artifacts, and tool outputs.

Agentic AI is changing how research is done. AI scientists can read papers, propose hypotheses, call models, and determine which experiments to prioritize next.... Agentic AI is changing how research is done. AI scientists can read papers, propose hypotheses, call models, and determine which experiments to prioritize next. First proving their value in software engineering, coding agents now write, test, and ship production code. Scientific research can be more demanding and iterative. Researchers continually evaluate evidence, refine hypotheses… Source

Comparative study of CNNs and attention models for bovid tooth segmentation under noisy annotations.

On-policy distillation analysis reveals substantial noise in teacher supervision yet student convergence is robust to it.

Tutorial on rotational equivariance in ML for 3D data covering physics, materials science, and computer vision applications.

Contextual learning framework addresses catastrophic forgetting and semantic shift in incremental named entity recognition.