AI.info
Latest Research — Page 54
Browse Latest Research on AI.info.
- BarcodeMamba+: Advancing State-Space Models for Fungal Biodiversity Research
- TruthfulRAG: Resolving Factual-level Conflicts in Retrieval-Augmented Generation with Knowledge Graphs
- Diffusion Representations for Fine-Grained Image Classification: A Marine Plankton Case Study
- Jackpot: Optimal Budgeted Rejection Sampling for Extreme Actor-Policy Mismatch Reinforcement Learning
- ATLAS: Adaptive Transfer Scaling Laws for Multilingual Pretraining, Finetuning, and Decoding the Curse of Multilinguality
- How Much Does the Hint Matter? Scope Conditions for Hindsight Self-Distillation in Financial Reasoning
- Explainable AI for the EU Right to Explanation: A Systematic Review of the Law-XAI Translation Gap
- SagaScale: A Realistic, Scalable, and High-Quality Long-Context Benchmark Built from Full-Length Novels
- Kernel-Based Evaluation of Conditional Biological Sequence Models
- Parallel Token Prediction for Language Models
- Local Hybrid Retrieval-Augmented Document QA
- LTX-2: Efficient Joint Audio-Visual Foundation Model
- Point Cloud Quantization through Multimodal Prompting for 3D Understanding
- ReasonEdit: Editing Vision-Language Models using Human Reasoning
- Noise Stability of Transformer Models
- SoftwareGym: Scaling Computer-Use Agent Training with Diverse Synthesized Software Environments
- LLM-Enhanced Multimodal House Price Prediction using Structured, Textual, and Visual Features
- InSight: A Benchmark for Agentic Claim Verification in Interactive Visualizations
- World of Workflows: A Benchmark for Bringing World Models to Enterprise Systems
- RECAP: Looking Once Is Not Enough for Vision-Language Reasoning
- DataVista: Diagnosing Multimodal LLMs on Data Video Understanding
- Graph Learning Is Suboptimal in Causal Bandits
- UM-Text: A Unified Multimodal Model for Image Understanding and Visual Text Editing
- IPQA: A Benchmark for Core Intent Identification in Personalized Question Answering
- VoxServe: Streaming-Centric Serving System for Speech Language Models
- "As Eastern Powers, I will veto." : An Investigation of Nation-level Bias of Large Language Models in International Relations
- BMAM: Brain-inspired Multi-Agent Memory Framework
- Multi-View Graph Learning with Graph-Tuple
- Variance Computation for Weighted Model Counting with Knowledge Compilation Approach
- To Mix or To Merge: Toward Multi-Domain Reinforcement Learning for Large Language Models
- Common to Whom? Regional Cultural Commonsense and LLM Bias in India
- Balancing Synthetic Data and Replay for Enhancing Task-Specific Capabilities
- RefBench-PRO: Perceptual and Reasoning Oriented Benchmark for Referring Expression Comprehension
- ContractScrub: A benchmark for final review of legal contracts
- TRIP-Bench: A Benchmark for Long-Horizon Interactive Agents in Real-World Scenarios
- FinHopper: A Progressive Multi-Hop Benchmark for Complex Financial Agents with Step-wise Evaluation
- IntReal: A Real-World Dataset and Benchmark for Multimodal Interleaved Generation
- Environments as Scaffold: Enriching Feedback to Bootstrap Self-Evolving Agents in Long-Horizon Tasks
- Orient Anything V2: Unifying Orientation and Rotation Understanding
- Mage-VL-Cowork: A Full Training Recipe to Learn Hybrid Computer Use From Evolved Harnesses