ScreenParse dataset and ScreenVLM model deliver dense screen parsing that outperforms larger VLMs on PageIoU and transfers to better UI grounding.
Cox, Ruchir Puri, and Rameswar Panda
9 Pith papers cite this work. Polarity classification is still indexing.
9
Pith papers citing it
citation-role summary
background 2
citation-polarity summary
roles
background 2polarities
background 2representative citing papers
Structured Recurrent Mixers enable algebraic switching between parallel training and recurrent inference representations, yielding higher throughput, concurrency, and training efficiency than comparable linear-complexity models on language tasks.
SynConfRoute routes code completions using syntax validation and token confidence, improving pass@1 by up to 31% on hard tasks and reducing accelerator usage by 58% versus always using the largest model.
6G networks need LLM-based agents in a layered semantic control plane to achieve autonomous intelligence, with empirical results showing that heterogeneous deployment across device-edge-core is required due to inherent tradeoffs in reasoning, latency, and efficiency.
SweetSpot is an analytical model from Transformer computational and memory complexity that identifies energy minima at short-to-moderate inputs and medium outputs, achieving 1.79% MAPE on H100 GPU measurements across multiple LLMs.
Fine-tuning 13 CodeLMs on a constructed CLB dataset with nine interaction types improves detection, with UniXcoder-base reaching F1 0.7407 and small models outperforming large ones.
Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.
The authors propose creating data probes—synthetic sequences from defined random processes—to reveal how data properties drive LLM behavior across workflow stages.
STPR uses LLMs to generate Python constraint functions from natural language instructions, then applies them via traditional search algorithms to point clouds in simulated Gazebo robot environments with reported full compliance.
citing papers explorer
-
ScreenParse: Moving Beyond Sparse Grounding with Complete Screen Parsing Supervision
ScreenParse dataset and ScreenVLM model deliver dense screen parsing that outperforms larger VLMs on PageIoU and transfers to better UI grounding.
-
Structured Recurrent Mixers for Massively Parallelized Sequence Generation
Structured Recurrent Mixers enable algebraic switching between parallel training and recurrent inference representations, yielding higher throughput, concurrency, and training efficiency than comparable linear-complexity models on language tasks.
-
SynConfRoute: Syntax-Aware Routing for Efficient Code Completion with Small CodeLLMs
SynConfRoute routes code completions using syntax validation and token confidence, improving pass@1 by up to 31% on hard tasks and reducing accelerator usage by 58% versus always using the largest model.
-
6G Needs Agents: Toward Agentic AI-Native Networks for Autonomous Intelligence
6G networks need LLM-based agents in a layered semantic control plane to achieve autonomous intelligence, with empirical results showing that heterogeneous deployment across device-edge-core is required due to inherent tradeoffs in reasoning, latency, and efficiency.
-
SweetSpot: An Analytical Model for Predicting Energy Efficiency of LLM Inference
SweetSpot is an analytical model from Transformer computational and memory complexity that identifies energy minima at short-to-moderate inputs and medium outputs, achieving 1.79% MAPE on H100 GPU measurements across multiple LLMs.
-
Fine-Tuning Code Language Models to Detect Cross-Language Bugs
Fine-tuning 13 CodeLMs on a constructed CLB dataset with nine interaction types improves detection, with UniXcoder-base reaching F1 0.7407 and small models outperforming large ones.
-
Not All RAGs Are Created Equal: A Component-Wise Empirical Study for Software Engineering Tasks
Retriever-side choices, particularly the retrieval algorithm, exert more influence on RAG performance than generator selection across code generation, summarization, and repair tasks.
-
Position: Let's Develop Data Probes to Fundamentally Understand How Data Affects LLM Performance
The authors propose creating data probes—synthetic sequences from defined random processes—to reveal how data properties drive LLM behavior across workflow stages.
-
"Don't Do That!": Guiding Embodied Systems through Large Language Model-based Constraint Generation
STPR uses LLMs to generate Python constraint functions from natural language instructions, then applies them via traditional search algorithms to point clouds in simulated Gazebo robot environments with reported full compliance.