SenseBench is the first physics-based benchmark with 10K+ instances and dual protocols to evaluate VLMs on remote sensing low-level perception and diagnostic description, revealing domain bias and specific failure modes.
hub Mixed citations
Rouge: A package for automatic evaluation of summaries
Mixed citation behavior. Most common role is method (57%).
22
Pith papers citing it
Method
57% of classified citations
hub tools
citation-role summary
method 4
background 3
citation-polarity summary
representative citing papers
At the critical temperature of the 2D Potts model (q>4), a disordered layer emerges between two ordered phases, and its boundaries converge to a Brownian watermelon under diffusive scaling.
EHR-derived standardized patients and dual-track evaluation reveal LLMs trail clinicians by 37.28 points on full psychiatric encounters, with mental-status assessment the main bottleneck.
PPU-Bench is a real-world benchmark exposing forget-retain trade-offs in MLLM unlearning and motivating Boundary-Aware Optimization to enforce intra-subject factual boundaries.
Evolutionary trees from LLM weights recover ground-truth training topologies and identify key datasets and layers through phenotypic analysis.
OmniScript is a new 8B omni-modal model that turns long cinematic videos into scene-by-scene scripts and matches top proprietary models on temporal localization and semantic accuracy.
R2ABench benchmark shows LLMs generate syntactically valid software architectures from requirements but produce structurally fragmented results due to weak relational reasoning.
Smoothie performs diffusion by smoothing token embeddings based on semantic similarity, outperforming prior diffusion models on sequence-to-sequence and unconditional text generation tasks.
ASTRA-QA is a benchmark for abstract document question answering that uses explicit topic sets, unsupported content annotations, and evidence alignments to enable direct scoring of coverage and hallucination.
LithoBench is a new multi-level benchmark showing that existing large multimodal models have substantial limitations in geological semantic understanding for remote sensing lithology interpretation.
ASTOR improves a single code LLM across four tasks by 9.0-9.5% over the best specialist and 7.5-12.8% over prior multi-task RL baselines via utility-driven data scheduling and adaptive KL regularization.
A contrastive visual forgetting technique constrained to the null space of retained knowledge enables targeted unlearning of visual concepts in MLLMs while preserving non-target visual and all textual knowledge.
Semantically invariant row and column permutations in tables can cause LLMs to output incorrect answers, and a gradient-based attack called ATP efficiently finds such permutations that degrade performance across many models.
XAI explanations should be narratives with continuous structure, cause-effect, fluency and diversity, and new metrics are needed to evaluate this better than standard NLP scores.
LFRAG advances multimodal RAG to block-level retrieval with layout segmentation and cross-attention fusion, reporting SOTA retrieval, 7.20% higher answer accuracy, and 73.07% lower token consumption on the new LFDocQA benchmark.
DeepSlide introduces a multi-agent system for full presentation preparation that matches baselines on slide quality but improves narrative flow, pacing, and script synergy via a new dual-scoreboard benchmark.
GrACE is a fine-tuned generative method that uses similarity to a special token embedding for real-time calibrated confidence in LLMs and enables efficient confidence-based test-time scaling.
A-MEM is a dynamic memory system for LLM agents that builds and refines an interconnected network of notes with agent-driven linking and evolution, showing performance gains over prior memory methods on six models.
GPT-4 as an LLM judge achieves over 80% agreement with human preferences on MT-Bench and Chatbot Arena, matching human agreement levels and providing a scalable evaluation method.
Reinforcement learning with a tunable control parameter and clinical reward enables precision-recall controllable radiology report generation that outperforms prior methods on MIMIC-CXR.
CodeWiki presents a unified framework for repository-level documentation across seven languages using hierarchical decomposition, recursive multi-agent processing, and multi-modal synthesis, outperforming DeepWiki by 4.73% on CodeWikiBench.
A systematic review that categorizes prompting strategies for LLM-based code summarization, assesses their effectiveness, and identifies gaps in research and evaluation practices.
citing papers explorer
-
SenseBench: A Benchmark for Remote Sensing Low-Level Visual Perception and Description in Large Vision-Language Models
SenseBench is the first physics-based benchmark with 10K+ instances and dual protocols to evaluate VLMs on remote sensing low-level perception and diagnostic description, revealing domain bias and specific failure modes.
-
Encoder-Free Human Motion Understanding via Structured Motion Descriptions
At the critical temperature of the 2D Potts model (q>4), a disordered layer emerges between two ordered phases, and its boundaries converge to a Brownian watermelon under diffusive scaling.
-
MentalHospital: A Virtual Environment for Evaluating Psychiatric Clinical Encounters
EHR-derived standardized patients and dual-track evaluation reveal LLMs trail clinicians by 37.28 points on full psychiatric encounters, with mental-status assessment the main bottleneck.
-
PPU-Bench:Real World Benchmark for Personalized Partial Unlearning in Vision Language Models
PPU-Bench is a real-world benchmark exposing forget-retain trade-offs in MLLM unlearning and motivating Boundary-Aware Optimization to enforce intra-subject factual boundaries.
-
Analysis and Explainability of LLMs Via Evolutionary Methods
Evolutionary trees from LLM weights recover ground-truth training topologies and identify key datasets and layers through phenotypic analysis.
-
OmniScript: Towards Audio-Visual Script Generation for Long-Form Cinematic Video
OmniScript is a new 8B omni-modal model that turns long cinematic videos into scene-by-scene scripts and matches top proprietary models on temporal localization and semantic accuracy.
-
Benchmarking Requirement-to-Architecture Generation with Hybrid Evaluation
R2ABench benchmark shows LLMs generate syntactically valid software architectures from requirements but produce structurally fragmented results due to weak relational reasoning.
-
Smoothie: Smoothing Diffusion on Token Embeddings for Text Generation
Smoothie performs diffusion by smoothing token embeddings based on semantic similarity, outperforming prior diffusion models on sequence-to-sequence and unconditional text generation tasks.
-
ASTRA-QA: A Benchmark for Abstract Question Answering over Documents
ASTRA-QA is a benchmark for abstract document question answering that uses explicit topic sets, unsupported content annotations, and evidence alignments to enable direct scoring of coverage and hallucination.
-
LithoBench: Benchmarking Large Multimodal Models for Remote-Sensing Lithology Interpretation
LithoBench is a new multi-level benchmark showing that existing large multimodal models have substantial limitations in geological semantic understanding for remote sensing lithology interpretation.
-
Schedule-and-Calibrate: Utility-Guided Multi-Task Reinforcement Learning for Code LLMs
ASTOR improves a single code LLM across four tasks by 9.0-9.5% over the best specialist and 7.5-12.8% over prior multi-task RL baselines via utility-driven data scheduling and adaptive KL regularization.
-
Null Space Constrained Contrastive Visual Forgetting for MLLM Unlearning
A contrastive visual forgetting technique constrained to the null space of retained knowledge enables targeted unlearning of visual concepts in MLLMs while preserving non-target visual and all textual knowledge.
-
The Power of Order: Fooling LLMs with Adversarial Table Permutations
Semantically invariant row and column permutations in tables can cause LLMs to output incorrect answers, and a gradient-based attack called ATP efficiently finds such permutations that degrade performance across many models.
-
On the Importance and Evaluation of Narrativity in Natural Language AI Explanations
XAI explanations should be narratives with continuous structure, cause-effect, fluency and diversity, and new metrics are needed to evaluate this better than standard NLP scores.
-
LFRAG: Layout-oriented Fine-grained Retrieval-Augmented Generation on Multimodal Document Understanding
LFRAG advances multimodal RAG to block-level retrieval with layout segmentation and cross-attention fusion, reporting SOTA retrieval, 7.20% higher answer accuracy, and 73.07% lower token consumption on the new LFDocQA benchmark.
-
DeepSlide: From Artifacts to Presentation Delivery
DeepSlide introduces a multi-agent system for full presentation preparation that matches baselines on slide quality but improves narrative flow, pacing, and script synergy via a new dual-scoreboard benchmark.
-
GrACE: A Generative Approach to Better Confidence Elicitation and Efficient Test-Time Scaling in Large Language Models
GrACE is a fine-tuned generative method that uses similarity to a special token embedding for real-time calibrated confidence in LLMs and enables efficient confidence-based test-time scaling.
-
A-MEM: Agentic Memory for LLM Agents
A-MEM is a dynamic memory system for LLM agents that builds and refines an interconnected network of notes with agent-driven linking and evolution, showing performance gains over prior memory methods on six models.
-
Judging LLM-as-a-Judge with MT-Bench and Chatbot Arena
GPT-4 as an LLM judge achieves over 80% agreement with human preferences on MT-Bench and Chatbot Arena, matching human agreement levels and providing a scalable evaluation method.
-
Precision Recall Controllable Radiology Report Generation via Hybrid Natural Language and Clinical Reward Learning
Reinforcement learning with a tunable control parameter and clinical reward enables precision-recall controllable radiology report generation that outperforms prior methods on MIMIC-CXR.
-
CodeWiki: Evaluating AI's Ability to Generate Holistic Documentation for Large-Scale Codebases
CodeWiki presents a unified framework for repository-level documentation across seven languages using hierarchical decomposition, recursive multi-agent processing, and multi-modal synthesis, outperforming DeepWiki by 4.73% on CodeWikiBench.
-
Prompt-Driven Code Summarization: A Systematic Literature Review
A systematic review that categorizes prompting strategies for LLM-based code summarization, assesses their effectiveness, and identifies gaps in research and evaluation practices.