AI Dataset2026
A multiple-choice benchmark for evaluating language-model arithmetic: 1,000 continuation-style elementary word problems (4 choices, balanced labels) organized by topic, grade band, and difficulty. Designed for base-model continuation log-likelihood scoring; released under Apache-2.0.
AI Dataset2026
A compact evaluation dataset and harness for testing agentic AI on safety-critical robotics tasks. Includes multimodal episodes in parquet format, task-specific eval scripts (gauge reading, human safety monitoring, VLA estimators), and TFDS/Hugging Face integration for reproducible safety evaluations.
Selects a referred target from candidate bounding boxes, then decodes tracking waypoints for single-camera embodied visual tracking. Injects past selected-bbox geometry via sliding-window TVBI tokens and is co-trained on a Refer‑QA dataset; achieves SOTA on EVT‑Bench and demonstrates sim-to-real on legged and humanoid robots.
Provides a unified survey of progress-reward modeling for robotic learning, detailing interfaces, modeling techniques, and evaluation practices. Organizes the literature into three perspectives—interface, model internals, and data/benchmarks—and highlights limitations and open problems. Useful for researchers designing rewards for long-horizon or sparse-reward robotic tasks.
Evaluates spatial cognition of image-generation models by eliciting protocol-constrained visual answers and parsing pixel outputs into structured predictions compatible with existing metrics. Introduces the ProVisE framework and SpatialGen-Bench (470 samples) to compare image-generation models and text-output VLMs on unified spatial tasks.
AI Dataset2026
Evaluates atomic visual perception of multimodal LLMs using 3,000 short visual questions that isolate ten perceptual skills. Built from an error taxonomy across 42 benchmarks, capability-balanced and accompanied by a model leaderboard.
Reranks multilingual retrieval candidates to favour documents that are both semantically relevant and written in the same language as the query, using English-anchored relevance distillation and preference alignment; excels in language-coherence tests while remaining competitive on standard multilingual reranking benchmarks.
Transforms open-ended LLM optimization into self-verifiable reinforcement learning by turning tasks into proxy environments that produce deterministic, rule-based rewards. Proposes RLSVR and SpyRL — an information-asymmetric self-play scheme where agents vote to identify a preassigned spy, yielding verifiable rewards without human annotation. Demonstrated on summarization, creative writing and mathematical reasoning.
AI Dataset2026
Provides a public test split of multimodal financial GUI interaction examples for evaluating agents that convert instructions and screenshots into grounded UI actions. Includes step-level screenshots, dialogue history, an OpenAI-style computer_use tool schema, and JSON next-action references; training data available on request.
Measures how agent memory systems miss implicitly associated facts by introducing InMind, a 125-task benchmark with paired controls that separate stored-vs-retrieval vs knowledge gaps. Quantifies a large retrieval-interface blind spot and points to routing as the core open problem.
Co-evolves a solver skill and a rubric-generator skill for text-space LLM optimization under decoupled objectives to avoid rubric gaming without using gold rubrics. Solver updates use criterion-level feedback; generator updates use independent audits of requirement coverage and response discrimination.
Allocates token-level credit in rubric-conditioned GRPO by counterfactually replaying the same response under rubric and criteria-free prompts, using tokenwise log-likelihood contrasts to compute bounded, response-normalized weights that redistribute GRPO advantages without training an auxiliary scorer.