Proposes WUICC task and WUICC-bench dataset, then evaluates 11 image difference captioning methods plus 2 LLMs on web UI changes.
hub
Bleu: a method for automatic evaluation of machine translation
12 Pith papers cite this work. Polarity classification is still indexing.
12
Pith papers citing it
hub tools
citation-role summary
method 1
citation-polarity summary
roles
method 1polarities
use method 1representative citing papers
S2ST-Omni 2 uses typology-informed hierarchical encoding, gated Dual-CTC, and typology-aware prompting to improve multilingual S2ST over flat-label baselines on CVSS-C, with gains in low-data regimes.
EKD trains lightweight NMT students progressively from a chain of teachers with rising capacity, achieving BLEU scores within 0.08 of the largest teacher on IWSLT-14.
RIHA proposes a hierarchical alignment transformer that uses multi-scale visual and textual feature pyramids plus optimal transport to generate more accurate radiology reports from medical images.
LLM-ReSum uses LLM self-evaluation in a closed feedback loop to refine summaries, improving factual accuracy by up to 33% and coverage by 39% with 89% human preference.
Rationale-guided fine-tuning plus dual-path adaptive inference lifts a 1.3B decompiler refiner to 50% average re-executability, a new lightweight SOTA on HumanEval-Decompile.
Chat-Scene++ improves 3D scene understanding in multimodal LLMs by representing scenes as context-rich object sequences with identifier tokens and grounded chain-of-thought reasoning, reaching state-of-the-art on five benchmarks using pre-trained encoders.
LLMLingua-2 at ~50% compression preserves semantics on LLaDA but substantially hurts GSM8K math accuracy, with failures driven more by omitted reasoning tokens than semantic drift.
A dependency-aware prompt pipeline with structured JSON intermediates produces coherent, scalable RPG worlds and quests from LLMs.
CoT prompting improves LLM performance on control-flow deobfuscation of C benchmarks, yielding ~16% better CFG reconstruction and ~20.5% better semantic preservation for GPT5 versus zero-shot prompting.
A globally video-guided multimodal translation framework retrieves semantically related video segments with a vector database and applies attention mechanisms to improve subtitle translation accuracy in long videos.
citing papers explorer
-
Beyond Pixel Diffs: Benchmarking Image Change Captioning for Web UI Visual Regression Testing
Proposes WUICC task and WUICC-bench dataset, then evaluates 11 image difference captioning methods plus 2 LLMs on web UI changes.
-
From Flat Language Labels to Typological Priors: Structured Language Conditioning for Multilingual Speech-to-Speech Translation
S2ST-Omni 2 uses typology-informed hierarchical encoding, gated Dual-CTC, and typology-aware prompting to improve multilingual S2ST over flat-label baselines on CVSS-C, with gains in low-data regimes.
-
Evolving Knowledge Distillation for Lightweight Neural Machine Translation
EKD trains lightweight NMT students progressively from a chain of teachers with rising capacity, achieving BLEU scores within 0.08 of the largest teacher on IWSLT-14.
-
RIHA: Report-Image Hierarchical Alignment for Radiology Report Generation
RIHA proposes a hierarchical alignment transformer that uses multi-scale visual and textual feature pyramids plus optimal transport to generate more accurate radiology reports from medical images.
-
LLM-ReSum: A Framework for LLM Reflective Summarization through Self-Evaluation
LLM-ReSum uses LLM self-evaluation in a closed feedback loop to refine summaries, improving factual accuracy by up to 33% and coverage by 39% with 89% human preference.
-
CoDe-R: Refining Decompiler Output with LLMs via Rationale Guidance and Adaptive Inference
Rationale-guided fine-tuning plus dual-path adaptive inference lifts a 1.3B decompiler refiner to 50% average re-executability, a new lightweight SOTA on HumanEval-Decompile.
-
Chat-Scene++: Exploiting Context-Rich Object Identification for 3D LLM
Chat-Scene++ improves 3D scene understanding in multimodal LLMs by representing scenes as context-rich object sequences with identifier tokens and grounded chain-of-thought reasoning, reaching state-of-the-art on five benchmarks using pre-trained encoders.
-
Prompt Compression in Diffusion Large Language Models: Evaluating LLMLingua-2 on LLaDA
LLMLingua-2 at ~50% compression preserves semantics on LLaDA but substantially hurts GSM8K math accuracy, with failures driven more by omitted reasoning tokens than semantic drift.
-
From World-Gen to Quest-Line: A Dependency-Driven Prompt Pipeline for Coherent RPG Generation
A dependency-aware prompt pipeline with structured JSON intermediates produces coherent, scalable RPG worlds and quests from LLMs.
-
Analyzing Chain of Thought (CoT) Approaches in Control Flow Code Deobfuscation Tasks
CoT prompting improves LLM performance on control-flow deobfuscation of C benchmarks, yielding ~16% better CFG reconstruction and ~20.5% better semantic preservation for GPT5 versus zero-shot prompting.
-
Video-guided Machine Translation with Global Video Context
A globally video-guided multimodal translation framework retrieves semantically related video segments with a vector database and applies attention mechanisms to improve subtitle translation accuracy in long videos.
- Retrofit: Continual Learning with Controlled Forgetting for Binary Security Detection and Analysis