🔒
Limited View Viewing last 7 days only. Sign up free to unlock all filters.
Filters
Clear all

Recent Research Signals

Found 44 results

Filtering papers...

Paper Possible Impact Features Possible Business Area
PaddleOCR-VL-1.5: Towards a Multi-Task 0.9B VLM for Robust In-the-Wild Document Parsing
CV and Pattern Recognition
Reads documents and recognizes seals better.
Baidu Code Data
Image Recognition (78%)
Score: 4
3 days ago
Towards Robust Dysarthric Speech Recognition: LLM-Agent Post-ASR Correction Beyond WER
Audio and Speech Processing
Fixes computer speech errors for clearer understanding.
Code Data 2 Countries
Speech Recognition (78%)
Score: 3
3 days ago
Mam-App: A Novel Parameter-Efficient Mamba Model for Apple Leaf Disease Classification
CV and Pattern Recognition
Finds apple diseases on phones with high accuracy.
Data 2 Countries
Machine Learning (75%)
Score: 3
3 days ago
Dynamic Thinking-Token Selection for Efficient Reasoning in Large Reasoning Models
Artificial Intelligence
Makes AI think faster by skipping extra steps.
Code Data
Natural Language Processing (78%)
Score: 3
6 days ago
AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts
Computation and Language
Tests AI's ability to solve tricky puzzles.
Code Data
Natural Language Processing (78%)
Score: 3
4 days ago
SAGE: Steerable Agentic Data Generation for Deep Search with Execution Feedback
Artificial Intelligence
Creates smart search tools that learn to answer hard questions.
Google Code Data
Semantic Search (81%)
Score: 3
6 days ago
Meta Context Engineering via Agentic Skill Evolution
Artificial Intelligence
Teaches computers to learn better and faster.
Code Data
Semantic Search (81%)
Score: 3
3 days ago
OmegaUse: Building a General-Purpose GUI Agent for Autonomous Task Execution
Artificial Intelligence
Helps computers do tasks on phones and computers.
Baidu Data
Android (77%)
Score: 3
4 days ago
Are Video Generation Models Geographically Fair? An Attraction-Centric Evaluation of Global Visual Knowledge
CV and Pattern Recognition
AI videos show world landmarks equally well.
Code Data
Image Recognition (79%)
Score: 3
6 days ago
When Life Gives You AI, Will You Turn It Into A Market for Lemons? Understanding How Information Asymmetries About AI System Capabilities Affect Mark…
Human-Computer Interaction
Helps people trust and use smart computer programs.
Code Data 4 Countries
Artificial Intelligence (82%)
Score: 3
3 days ago
Typhoon-S: Minimal Open Post-Training for Sovereign Large Language Models
Computation and Language
Makes AI understand local languages and laws.
Code Data
Natural Language Processing (77%)
Score: 3
6 days ago
CovertComBench: The First Domain-Specific Testbed for LLMs in Wireless Covert Communication
Networking and Internet Architecture
Teaches AI to hide secret messages securely.
Data 3 Countries
Darknet (76%)
Score: 3
6 days ago
AgentLongBench: A Controllable Long Benchmark For Long-Contexts Agents via Environment Rollouts
Computation and Language
Tests AI's ability to solve puzzles with changing clues.
Code Data
Natural Language Processing (78%)
Score: 3
4 days ago
RedSage: A Cybersecurity Generalist LLM
Cryptography and Security
Helps computers understand and fight cyber threats.
Code Data
Legal Tech (78%)
Score: 2
3 days ago
Calibrating Beyond English: Language Diversity for Better Quantized Multilingual LLM
Computation and Language
Makes AI understand many languages better.
Code Data
Natural Language Processing (77%)
Score: 2
6 days ago
Digital Euro: Frequently Asked Questions Revisited
Computers and Society
Digital euro may spy on your money.
Data 2 Countries
Virtual Currency (83%)
Score: 2
6 days ago
GhostUI: Unveiling Hidden Interactions in Mobile UI
Human-Computer Interaction
Helps apps find secret buttons and do tasks.
Code Data
UX Design (79%)
Score: 2
5 days ago
Group Distributionally Robust Optimization-Driven Reinforcement Learning for LLM Reasoning
Machine Learning (CS)
Teaches AI to solve harder problems faster.
Tencent Data
A/B Testing (75%)
Score: 2
5 days ago
Innovator-VL: A Multimodal Large Language Model for Scientific Discovery
CV and Pattern Recognition
Teaches computers to understand science with less data.
Code Data
Natural Language Processing (80%)
Score: 2
5 days ago
Perturbation-Induced Linearization: Constructing Unlearnable Data with Solely Linear Classifiers
Machine Learning (CS)
Makes AI forget private info in pictures.
Code Data
Machine Learning (77%)
Score: 2
5 days ago
DuwatBench: Bridging Language and Visual Heritage through an Arabic Calligraphy Benchmark for Multimodal Understanding
CV and Pattern Recognition
Helps computers read fancy Arabic writing.
Code Data
Image Recognition (76%)
Score: 2
5 days ago
An Empirical Evaluation of Modern MLOps Frameworks
Software Engineering
Helps pick the best AI tools for jobs.
Code Data
Machine Learning (82%)
Score: 2
4 days ago
SokoBench: Evaluating Long-Horizon Planning and Reasoning in Large Language Models
Artificial Intelligence
Computers struggle to plan many steps ahead.
Data
Natural Language Processing (80%)
Score: 2
4 days ago
FrontierScience: Evaluating AI's Ability to Perform Expert-Level Scientific Tasks
Artificial Intelligence
Tests if AI can do hard science problems.
OpenAI Data
Artificial Intelligence (82%)
Score: 2
4 days ago
From Linear Input to Hierarchical Structure: Function Words as Statistical Cues for Language Learning
Computation and Language
Helps computers learn language structure faster.
Code Data
Natural Language Processing (79%)
Score: 2
4 days ago
HER: Human-like Reasoning and Reinforcement Learning for LLM Role-playing
Machine Learning (CS)
Makes AI characters think like real people.
Code Data
Virtual Reality (78%)
Score: 2
3 days ago
Topeax -- An Improved Clustering Topic Model with Density Peak Detection and Lexical-Semantic Term Importance
Artificial Intelligence
Finds better main ideas in long texts.
Code Data
Text Analytics (78%)
Score: 2
3 days ago
LAMP: Look-Ahead Mixed-Precision Inference of Large Language Models
Machine Learning (CS)
Makes AI smarter and faster using less power.
Code Data
Natural Language Processing (79%)
Score: 2
3 days ago
AdaptBPE: From General Purpose to Specialized Tokenizers
Computation and Language
Makes computer language understanding better for specific topics.
Code Data
Natural Language Processing (77%)
Score: 2
3 days ago
Mind the Gap: How Elicitation Protocols Shape the Stated-Revealed Preference Gap in Language Models
Artificial Intelligence
Makes AI's choices match its stated values.
Code Data
Semantic Search (75%)
Score: 2
3 days ago
LungCRCT: Causal Representation based Lung CT Processing for Lung Cancer Treatment
CV and Pattern Recognition
Finds lung cancer causes to improve treatments.
Code Data
Image Recognition (77%)
Score: 2
6 days ago
Foresight Learning for SEC Risk Prediction
Machine Learning (CS)
Helps predict company problems using old reports.
Data
Predictive Analytics (77%)
Score: 1
5 days ago
Unifying Speech Editing Detection and Content Localization via Prior-Enhanced Audio LLMs
Sound
Finds fake speech made by computers.
Data
Natural Language Processing (78%)
Score: 1
3 days ago
Hierarchical Text Classification with LLM-Refined Taxonomies
Computation and Language
Fixes messy categories so computers understand them better.
Data
Semantic Search (77%)
Score: 1
6 days ago
Clustering Methods for Identifying and Modelling Areas with Similar Temperature Variations
Applications
Predicts future global warming patterns more accurately.
Data
Predictive Analytics (78%)
Score: 1
3 days ago
BengaliSent140: A Large-Scale Bengali Binary Sentiment Dataset for Hate and Non-Hate Speech Classification
Computation and Language
Helps computers understand angry Bengali words better.
Data
Natural Language Processing (77%)
Score: 1
5 days ago
Enabling SSI-Compliant Use of EUDI Wallet Credentials through Trusted Execution Environment and Zero-Knowledge Proof
Emerging Technologies
Gives you control of your digital ID.
Data
Identity Management (81%)
Score: 1
5 days ago
Opinion Consensus Formation Among Networked Large Language Models
Social and Information Networks
AI groups agree, but not how we expect.
Data
Crowdsourcing (77%)
Score: 1
3 days ago
Multi-Robot Decentralized Collaborative SLAM in Planetary Analogue Environments: Dataset, Challenges, and Lessons Learned
Robotics
Robots map new places together without talking much.
Data
Robotics (79%)
Score: 1
4 days ago
OSIRIS: Bridging Analog Circuit Design and Machine Learning with Scalable Dataset Generation
Machine Learning (CS)
Builds computer chips faster and better.
Data
Intelligent Systems (81%)
Score: 1
5 days ago
Not All Code Is Equal: A Data-Centric Study of Code Complexity and LLM Reasoning
Machine Learning (CS)
Makes AI smarter by teaching it organized code.
Data
Natural Language Processing (80%)
Score: 1
3 days ago
MGSM-Pro: A Simple Strategy for Robust Multilingual Mathematical Reasoning Evaluation
Computation and Language
Tests math AI better in many languages.
Data
A/B Testing (76%)
Score: 1
3 days ago
GAVEL: Towards rule-based safety through activation monitoring
Artificial Intelligence
Makes AI safer by understanding its hidden thoughts.
Data
Natural Language Processing (80%)
Score: 1
5 days ago
GAVEL: Towards rule-based safety through activation monitoring
Artificial Intelligence
Makes AI safer by understanding its hidden thoughts.
Data
Natural Language Processing (80%)
Score: 1
5 days ago