Entities · Models
Gemini 2.5 Pro
64 articles tagged with this entity.
-
EgoPolice: A Benchmark for Egocentric Video Understanding in High-Stakes Police Body-Worn Camera Footage
-
Multi-Task Instruction Tuning via Data Scheduling for Low-Resource Arabic SpeechLLMs
-
FirstResearch: Auditable Question Formation for LLM Scientific Discovery Agents
-
Agent Data Injection Attacks are Realistic Threats to AI Agents
-
Decomposed Prompting Does Not Fix Knowledge Gaps, But Helps Models Say "I Don't Know"
-
AI Wizards at EXIST 2026: Hierarchical Soft-Label Learning for Multimodal Sexism Identification in Memes
-
The only AI glossary you’ll need this year
-
Certified Speculative Execution for Untrusted AI Agents
-
Theory of Mind and Persuasion Beyond Conversation: Assessing the Capacity of LLMs to Induce Belief States via Planning and Action
-
Search for Truth from Reasoning: A Dynamic Representation Editing Framework for Steering LLM Trajectories
-
Agent-Computer Observation Interfaces Enable Dynamic Computer Use
-
SEVA: Self-Evolving Verification Agent with Process Reward for Fact Attribution
-
Fine-tuning a multimodal large language model for clinician-grade autism behavioral scoring from short home videos
-
Epiphany-Aware KV Cache Eviction Without the Attention Matrix
-
An Empirical Study of LLM-Generated Specifications for VeriFast
-
6 Fingers, 1 Kidney: Natural Adversarial Medical Images Reveal Critical Weaknesses of Vision-Language Models
-
Which tokens does a hybrid model predict better?
-
Perfect Detection, Failed Control: The Geometry of Knowing vs. Steering in Language Models
-
Detect, Unlearn, Restore: Defending Text Summarization Models Against Data Poisoning
-
Import AI 462: Superpersuasion; self-sustaining AI; paths to ASI
-
Beyond Entropy: Learning from Token-Level Distributional Deviations for LLM Reasoning
-
Ensembles of Large Language Models for Identifying EQ-5D Studies in PubMed Based on Their Abstracts
-
AI-Driven Assessment of Human Tutors: Linking Training Performance to Real-Life Practice
-
Querying an astronomical database using large language models: the ALeRCE text-to-SQL system
-
Trust Between AI Agents: Measuring Formation, Breakage, and Recovery, with Implications for Governing Multi-Agent Systems
-
Whose hotel does the AI recommend? An algorithm audit of reputation signals in LLM-assisted hotel selection
-
HanDyVQA: A Video QA Benchmark for Fine-Grained Hand-Object Interaction Dynamics
-
Closing the Auto-Research Loop: An AI Co-Scientist for Production Search Ranking
-
The Quality-Utility Paradox: Why High-Reward Data Impairs Small Model Mathematical Reasoning
-
No Accidental Software Agent First Canonical Code for Human Code Entropy Reduction and 30 to 500 times Lower Frontier Model Requirements
-
A Two-Stage Statistical Framework for Evaluating Associative Interference in Large Language Models
-
Dense Coordinate-List Fine-Tuning Induces a Controllable Interference Surface in Vision-Language Models
-
GeoNatureAgent Benchmark: Benchmarking LLM Agents for Environmental Geospatial Analysis Across Frontier and Open-Weight Foundation Models
-
Who Brought Easter Eggs to Eid? Auditing Cultural Translation of Math Word Problems Across Diverse Languages and Regions
-
Beyond Model Size: Probing the Gaps in Visual in-Context Learning by Training a Tiny Model
-
Claude Fable 5 and new AI safety fables
-
What it feels like to work with Mythos
-
Benchmarking Open-Ended Multi-Agent Coordination in Language Agents
-
Language-based Trial and Error Falls Behind in the Era of Experience
-
The crash that vanished: control and emergence in a five-model economy
-
Probing Multimodal Large Language Models on Cognitive Biases in Chinese Short-Video Misinformation
-
Exploring LLMs for South Asian Music Understanding and Generation
-
AgentDisCo: Towards Disentanglement and Collaboration in Open-ended Deep Research Agents
-
Towards One-to-Many Temporal Grounding
-
Before and After Temperature: A Distributional View of Creative LLM Generation
-
FinVerBench: Benchmark Validity and Calibration in Large Language Model Financial Statement Verification
-
unix-ctf: Procedural Environments for Unix-Competence Reinforcement Learning
-
MedMosaic: A Challenging Large Scale Benchmark of Diverse Medical Audio
-
Hilbert-Geo: Solving Solid Geometric Problems by Neural-Symbolic Reasoning
-
Training Deliberative Monitors for Black-Box Scheming Detection
-
Using Zero-Shot LLM-Generated Survey Data for Geographically Explicit Population Synthesis
-
AdvJudge-Zero: Binary Decision Flips in LLM-as-a-Judge via Adversarial Control Tokens
-
I’m a Professional Fact-Checker. AI Is Wrong More Often Than You Think
-
Depth Registers Unlock W4A4 on SwiGLU: A Reader/Generator Decomposition
-
BC Protocol: Structured Dual-Expert Dialogue for Eliciting High-Quality Chain-of-Thought Post-Training Data
-
Chain-of-Thought Hijacking
-
UtilityMax Prompting: A Formal Framework for Multi-Objective Large Language Model Tasks
-
TempRet: Temporal Enhancement and Two-Stage Reranking for CVPR 2026 EPIC-KITCHENS-100 Multi-Instance Retrieval Challenge
-
Merge-Bench: Resolve Merge Conflicts with Large Language Models
-
WhenLoss: Diagnosing Write and Retrieval Bottlenecks in Long-Context Memory Systems
-
MDIA: A Multi-Agent Diagnostic Intelligence Pipeline on HealthBench Professional
-
Co-ReAct: Rubrics as Step-Level Collaborators for ReAct Agents
-
Selective LoRA for Visual Tokens and Attention Heads
-
State Stream Transformer (SST) V2: Parallel Training of Nonlinear Recurrence for Latent Space Reasoning