TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
Canonical reference
Dataflow: An llm-driven framework for unified data preparation and workflow automation in the era of data-centric ai
Canonical reference. 80% of citing Pith papers cite this work as background.
9
Pith papers citing it
Background
80% of classified citations
citation-role summary
background 4
baseline 1
citation-polarity summary
years
2026 9representative citing papers
PopPy combines an ahead-of-time compiler and runtime to extract parallelism from Python compound AI applications, delivering up to 6.4x end-to-end speedups while preserving sequential semantics.
K12-KGraph is a textbook-derived knowledge graph that powers a new benchmark revealing LLMs' poor curriculum cognition and a small training corpus that outperforms general instruction data on educational tasks.
Benchmark Agent is an autonomous agentic system that constructs benchmarks for LLMs and MLLMs via query analysis, subtask design, annotation and quality control, yielding 15 benchmarks with minimal human input.
Structured knowledge extracted from corpora enables test-driven data engineering for LLMs by mapping training data to source code, model training to compilation, benchmarking to unit testing, and failures to targeted data repairs, demonstrated across 16 disciplines.
TREX automates the LLM training lifecycle via collaborative agents and tree-based exploration, delivering consistent performance gains across 10 real-world fine-tuning tasks in FT-Bench.
AAFLOW is a unified distributed runtime that models agentic workflows as operators with a zero-copy data plane using Apache Arrow and Cylon, achieving up to 4.64x pipeline speedup through improved data flow and batching.
DataArc-SynData-Toolkit is an open-source, configuration-driven framework that unifies synthetic data generation for multimodal, multilingual, and multi-task LLM training with improved usability and quality control.
citing papers explorer
-
TraceAV-Bench: Benchmarking Multi-Hop Trajectory Reasoning over Long Audio-Visual Videos
TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
-
PopPy: Opportunistically Exploiting Parallelism in Python Compound AI Applications
PopPy combines an ahead-of-time compiler and runtime to extract parallelism from Python compound AI applications, delivering up to 6.4x end-to-end speedups while preserving sequential semantics.
-
K12-KGraph: A Curriculum-Aligned Knowledge Graph for Benchmarking and Training Educational LLMs
K12-KGraph is a textbook-derived knowledge graph that powers a new benchmark revealing LLMs' poor curriculum cognition and a small training corpus that outperforms general instruction data on educational tasks.
-
Benchmark Everything Everywhere All at Once
Benchmark Agent is an autonomous agentic system that constructs benchmarks for LLMs and MLLMs via query analysis, subtask design, annotation and quality control, yielding 15 benchmarks with minimal human input.
-
Programming with Data: Test-Driven Data Engineering for Self-Improving LLMs from Raw Corpora
Structured knowledge extracted from corpora enables test-driven data engineering for LLMs by mapping training data to source code, model training to compilation, benchmarking to unit testing, and failures to targeted data repairs, demonstrated across 16 disciplines.
-
TREX: Automating LLM Fine-tuning via Agent-Driven Tree-based Exploration
TREX automates the LLM training lifecycle via collaborative agents and tree-based exploration, delivering consistent performance gains across 10 real-world fine-tuning tasks in FT-Bench.
-
AAFLOW: Scalable Patterns for Agentic AI Workflows
AAFLOW is a unified distributed runtime that models agentic workflows as operators with a zero-copy data plane using Apache Arrow and Cylon, achieving up to 4.64x pipeline speedup through improved data flow and batching.
-
DataArc-SynData-Toolkit: A Unified Closed-Loop Framework for Multi-Path, Multimodal, and Multilingual Data Synthesis
DataArc-SynData-Toolkit is an open-source, configuration-driven framework that unifies synthetic data generation for multimodal, multilingual, and multi-task LLM training with improved usability and quality control.
- OpenWorldLib: A Unified Codebase and Definition of Advanced World Models