AI.info
Latest Research — Page 45
Browse Latest Research on AI.info.
- Scaling Parameter-Efficient Fine-Tuning for Brain Encoding
- Multi-Stream Attention Residuals
- OR-R1: Automating Modeling and Solving of Operations Research Optimization Problem via Test-Time Reinforcement Learning
- Learning Representations to Guide Pixel Diffusion Transformers
- CUAWright: A Minimal Unified Interface for Digital Agents
- Adaptive Multi-Agent Response Refinement in Conversational Systems
- OpenFlyV2: An onboard vision-language-action model for aerial perception and navigation
- From Production Traffic to Post-Training: Building a Self-Hosted LLM That Covers the Corporate Request Mix
- LLM-VA: Resolving the Jailbreak-Overrefusal Trade-off via Vector Alignment
- [Re] Benchmarking LLM Capabilities in Negotiation through Scoreable Games
- Neuro-Symbolic Agents for Regulated Process Automation: Challenges and Research Agenda
- Mitigating Staleness in Asynchronous Pipeline Parallelism via Basis Rotation
- From Cause to Effect: Generating Intermediate Event Chains in Videos
- STATUS Bench: A Rigorous Benchmark for Evaluating Object State Understanding in Vision-Language Models
- Intellectual Property Protection for 3D Gaussian Splatting Assets: A Survey
- Cyclic Counterfactuals under Shift-Scale Interventions
- Wave Forcing: Towards Speed-of-Light Streaming Video Generation
- Percolation Dynamics in Optimization : Variance Cascades and Discrete Scale Invariance
- Your Language Model Secretly Contains Personality Subnetworks
- Learning Pseudo-Riemannian Manifolds for Heterophilic Graphs via Graph Signature
- FlowState: Execution State as Memory for Long-Horizon LLM Agents
- Compendia: Automated Visual Storytelling Generation from Online Article Collection
- LimRank: Less is More for Reasoning-Intensive Information Reranking
- OmniCast: A Masked Latent Diffusion Model for Weather Forecasting Across Time Scales
- Rubric-to-Code Credit Assignment for Reinforcement Learning
- OmniFusion: Simultaneous Multilingual Multimodal Translations via Modular Fusion
- Rethinking Sequence Compression with Test-time Regression
- Thunder-KoNUBench: A Corpus-Aligned Benchmark for Korean Negation Understanding
- Collective Narrative Grounding: Community-Coordinated Data Contributions to Improve Local AI Systems
- LTGS: Long-Term Gaussian Scene Chronology From Sparse View Updates
- PIPHEN: Physical Interaction Prediction with Hamiltonian Energy Networks
- CyIN: Cyclic Informative Latent Space for Bridging Complete and Incomplete Multimodal Learning
- Test-Time Mixture of World Models for Embodied Agents in Dynamic Environments
- SPRig: Self-Supervised Pose-Invariant Rigging from Mesh Sequences
- Axial Neural Networks for Dimension-Free Foundation Models
- Seeing the Unseen: Unified Visible--Invisible Motion for Physically Consistent Video Generation
- Beyond Prompts: A Systematic Study of LLM-Based Machine Translation Evaluators
- Learning Multimodal Embeddings for Traffic Accident Prediction and Causal Estimation
- WorldCast: Exploring Intelligent Visual Generation in World State Prediction
- Multi-Step Tool-Calling over Korean Open Public APIs: A Benchmark and a Data-Synthesis Recipe