AI.info

Latest Research — Page 89

Browse Latest Research on AI.info.

• Inference-Cost-Aware Dynamic Tree Construction for Efficient Inference in Large Language Models
• TransBiolab: A Real-World Multi-View Dataset of Cluttered Transparent Biomedical Objects
• Liars' Bench: Evaluating Lie Detectors for Language Models
• Hyperspectral data augmentation with transformer-based diffusion models
• Lost in the Maze: Overcoming Context Limitations in Long-Horizon Agentic Search
• DialFork: Going Beyond Factuality to Evaluate Procedural Hallucination in Conversational Agents
• PersonaMem-v2: Towards Personalized Intelligence via Learning Implicit User Personas and Agentic Memory
• AgentVQA: A Unified Benchmark for Agentic Visual Understanding
• When Token Pruning is Worse than Random: Understanding Visual Token Information in VLLMs
• NADIR: Differential Attention Flow for Non-Autoregressive Transliteration in Indic Languages
• Wasserstein-Barycentric Interaction Fields for Spatial Factor Models: Evidence from Language-Model Representations
• TREK: A Travel Reasoning and Evaluation Kit for LLM Agents in Complex Trip Planning
• FIT to Forget: Robust Continual Unlearning for Large Language Models
• EMFusion: Uncertainty-Aware Conditional Diffusion Model for Multivariate Narrow-band Exposure Forecasting
• EPSegFZ: Efficient Point Cloud Semantic Segmentation for Few- and Zero-Shot Scenarios with Language Guidance
• SnapMLA: Efficient Long-Context MLA Decoding via Hardware-Aware FP8 Quantized Pipelining
• BenchOverflow: Measuring Overflow in Large Language Models via Plain-Text Prompts
• A Modular Agent for Reliable and Auditable Spatial Relation Verification in CT Scans
• TokEval: A Tokenizer Evaluation Suite
• Are Stereotypes Leading LLMs' Zero-Shot Stance Detection ?
• ProcessPrefBench: Evaluating Cross-Task Transfer of Individual Process Preferences from Naturalistic Human-AI Interaction
• ChatR1: Reinforcement Learning for Conversational Reasoning and Retrieval Augmented Question Answering
• A Multicenter Benchmark of Multiple Instance Learning Models for Lymphoma Subtyping from HE-stained Whole Slide Images
• Is Knowledge Distillation Actually Greener? A Case Study in Machine Translation
• TimeLens: Rethinking Video Temporal Grounding with Multimodal LLMs
• Revisiting Complete Reasoning Traces for Post-Training
• DADO: A Depth-Attention framework for Object Discovery
• Post-Training Language Models for Gold-Medal Performance in Coding Competitions
• RefAtomNet++: Advancing Referring Atomic Video Action Recognition using Semantic Retrieval based Multi-Trajectory Mamba
• EmoMed: An Emotionally-Aware Agent for Multimodal Medical Support with Real-Time Information Retrieval
• Hybrid-grained Feature Aggregation with Coarse-to-fine Language Guidance for Self-supervised Monocular Depth Estimation
• Convolutional Spiking-based GRU Cell for Spatio-temporal Data
• Resisting Manipulative Bots in Meme Coin Copy Trading: A Multi-Agent Approach with Chain-of-Thought Reasoning
• Motion Attribution for Video Generation
• EdgeKernelBench: Unified LLM-Driven Kernel Generation for Edge Backends
• Spot The Ball: A Benchmark for Visual Social Inference
• AirNav: A Large-Scale UAV Vision-and-Language Navigation Dataset with Natural and Diverse Instructions
• Long Grounded Thoughts: Synthesizing Visual Problems and Reasoning Chains at Scale
• Towards Detecting AI-Assisted Responses in Online Surveys
• Prompting-in-a-Series: Psychology-Informed Contents and Embeddings for Personality Recognition With Decoder-Only Models