EHRNote-ChatQA is the first benchmark for evidence-grounded multi-turn clinical QA over longitudinal discharge summaries, containing 16,072 medical-expert-verified pairs across eight categories and revealing LLM weaknesses in evidence grounding and multi-turn consistency.
mega hub Mixed citations
Gemini 2.5: Pushing the Frontier with Advanced Reasoning, Multimodality, Long Context, and Next Generation Agentic Capabilities
Mixed citation behavior. Most common role is background (55%).
1032
Pith papers citing it
Background
55% of classified citations
abstract
In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. Gemini 2.5 Flash provides excellent reasoning abilities at a fraction of the compute and latency requirements and Gemini 2.0 Flash and Flash-Lite provide high performance at low latency and cost. Taken together, the Gemini 2.X model generation spans the full Pareto frontier of model capability vs cost, allowing users to explore the boundaries of what is possible with complex agentic problem solving.
hub tools
citation-role summary
background 122
baseline 46
method 28
other 8
dataset 3
citation-polarity summary
claims ledger
- abstract In this report, we introduce the Gemini 2.X model family: Gemini 2.5 Pro and Gemini 2.5 Flash, as well as our earlier Gemini 2.0 Flash and Flash-Lite models. Gemini 2.5 Pro is our most capable model yet, achieving SoTA performance on frontier coding and reasoning benchmarks. In addition to its incredible coding and reasoning skills, Gemini 2.5 Pro is a thinking model that excels at multimodal understanding and it is now able to process up to 3 hours of video content. Its unique combination of long context, multimodal and reasoning capabilities can be combined to unlock new agentic workflows. G
authors
mega hub controls
export citing contexts JSON
export graph JSON
export full bundle JSON
open full Pith review
annotated reader queued
Recognition alignment
counterfactual ablation
co-cited works
representative citing papers
HKJudge is a new ~290k-sentence expert-annotated corpus of Hong Kong criminal judgments with 26 rhetorical roles and 3 sentencing elements, plus benchmarks on classification and extraction tasks.
Introduces the first longitudinal voice dataset for RRP with benchmarks across handcrafted features, deep networks, self-supervised models, and audio LLMs under patient-level validation.
VideoFDB is a new benchmark and LM-as-judge framework for evaluating full-duplex audio-visual-to-audio-visual conversational agents on nonverbal dynamics from real video calls.
EgoIntrospect provides the first egocentric dataset with self-annotations for internal state tasks and shows multimodal LLMs struggle to infer subjective states from combined signals.
Persona vectors form within the first 0.22% of LLM pretraining and remain effective for steering post-trained models, with continued refinement and transfer to other models.
Sieve dynamically schedules MoE experts across GPU and PIM hardware to handle bimodal token distributions, achieving 1.3x to 1.6x gains in throughput and interactivity over static prior PIM systems on three large models.
M³Att poisons medical multimodal RAG by pairing covert textual misinformation with query-agnostic visual perturbations that increase retrieval of the bad content, causing LLMs to generate clinically plausible but incorrect responses.
Omni-DeepSearch is a 640-sample benchmark for audio-driven omni-modal search where the best model reaches only 43.44% accuracy, exposing bottlenecks in audio inference, tool use, and cross-modal reasoning.
TraceAV-Bench is the first benchmark for multi-hop trajectory reasoning over long audio-visual videos, showing top models reach only 51-68% accuracy with substantial room for improvement.
S1-VL combines structured scientific reasoning with iterative image manipulation via code execution to reach state-of-the-art results on visual and scientific reasoning benchmarks.
MM-JudgeBench shows substantial cross-lingual performance variance in 22 LVLM judges, with model size and architecture as poor predictors of multilingual robustness.
HalluAudio is the first large-scale benchmark spanning speech, environmental sound, and music that uses human-verified QA pairs, adversarial prompts, and mixed-audio tests to measure hallucinations in large audio-language models.
VLMs hallucinate by prioritizing contradictory on-screen text over visual content, addressed via the VisualTextTrap benchmark with 6,057 human-validated samples and the VTHM-MoE dual-encoder framework using dimension-specific experts and adaptive routing.
Large language models display the identifiable victim effect at roughly twice the human baseline, strongly amplified by instruction tuning and chain-of-thought prompting but inverted by reasoning-specialized models.
MMRareBench provides 1,756 QA pairs and 7,958 images from PMC rare-disease cases to evaluate 23 MLLMs, revealing low treatment-planning scores and medical models underperforming general models on multi-image tasks due to capacity dilution.
HM-Bench is the first benchmark for MLLMs on hyperspectral images, showing models struggle with complex spatial-spectral reasoning and perform better with visual PCA images than textual reports.
DialBGM is a new benchmark dataset revealing that existing AI models fall far short of human performance when recommending fitting background music for open-domain conversations.
V2X-QA provides a view-decoupled benchmark showing infrastructure views aid macroscopic traffic understanding while cooperative reasoning requires explicit cross-view alignment, with V2X-MoE as a routing-based baseline that improves performance.
ScreenParse dataset and ScreenVLM model deliver dense screen parsing that outperforms larger VLMs on PageIoU and transfers to better UI grounding.
EgoSound is a new benchmark with 7315 QA pairs across seven tasks to evaluate egocentric sound understanding in multimodal large language models.
VLRS-Bench is the first benchmark dedicated to complex vision-language reasoning in remote sensing, with 2000 QA pairs across 14 tasks in cognition, decision, and prediction dimensions.
Molmo2 delivers state-of-the-art open-weight video VLMs with new grounding datasets and training methods that outperform prior open models and match or exceed some proprietary ones on pointing and tracking tasks.
ConceptPose delivers state-of-the-art zero-shot relative pose estimation by matching open-vocabulary 3D concept vectors derived from VLM saliency maps, beating the strongest baseline by 62% in ADD(-S) without training.
citing papers explorer
-
ParseFixer: An Agentic Framework for Document Parsing via Selective Multimodal Correction
ParseFixer combines full-page backbone parsing with agentic selective multimodal correction to reach third place (score 61.78) in the DataMFM Challenge Track 1.
-
Reducing Token Usage of State-in-Context Agents using Minification
Code minification reduces average input token usage by 42% in state-in-context agents with a 12 percentage point drop in resolution rate on SWE-bench Verified.
-
CuriosAI Submission to the CASTLE Challenge at EgoVis 2026
Reports SVA (0.50) and TMKG (0.35) accuracies on the CASTLE 2026 egocentric video QA challenge using VLM/LLM pipelines with preprocessing.
-
Toward Native Multimodal Modeling: A Roadmap
A roadmap that defines architectural nativity for multimodal models and categorizes them into Multi-to-Text, Multi-to-Target, and Multi-to-Multi types while outlining an industrial pipeline toward unified transformer-based native multimodal modeling.
-
Understanding the Impact of Geometric Foundation Models on Vision-Language-Action Models
The paper quantifies the geometric gap in current VLAs via linear probing and compares three architectures for injecting geometry from GFMs while analyzing impacts of data, cameras, and reconstruction quality.
-
OmniEgo-R$^2$: A Routed Reasoning Framework for the 1st Cross-Domain EgoCross Challenge at CVPR 2026
OmniEgo-R² is a competition system that combines domain-specific VL models with temporal normalization, capability routing, and answer calibration to reach 66.35-66.77% accuracy on the EgoCross challenge.
-
U-CESE: Unified Clip-based Event Search Engine for AI Challenge HCMC 2025
U-CESE integrates three CESE modules into a unified clip-based pipeline with DAKE keyframe extraction and ReCap captioning to support consistent multimodal event retrieval across video sources.
-
Retrieval-Augmented Long-Context Translation for Cultural Image Captioning: Gators submission for AmericasNLP 2026 shared task
A retrieval-augmented two-stage system using Qwen2.5-VL for Spanish captions and Gemini 2.5 Flash for target-language generation achieves over 120% chrF++ gains on three Indigenous languages and wins the shared task.
-
A Survey of Reinforcement Learning for Large Reasoning Models
A survey compiling RL methods, challenges, data resources, and applications for enhancing reasoning in large language models and large reasoning models since DeepSeek-R1.
-
Evaluating Advanced Prompting on Gemini Flash for Multi-Hop Biomedical QA
Sophisticated prompting on Gemini 2.0 Flash achieves a 0.720 Concept Level Score on MedHopQA, outperforming baseline by 0.155 and matching Gemini 2.5 Flash performance.
-
BIT.UA-AAUBS at ArchEHR-QA 2026: Evaluating Open-Source and Proprietary LLMs via Prompting in Low-Resource QA
Prompt-based LLM evaluation without training data secured top rankings in the ArchEHR-QA 2026 shared task on clinical QA.
- DialToM: A Theory of Mind Benchmark for Forecasting State-Driven Dialogue Trajectories
- HyLaR: Hybrid Latent Reasoning with Decoupled Policy Optimization
- InHabit: Leveraging Image Foundation Models for Scalable 3D Human Placement
- HarDBench: A Benchmark for Draft-Based Co-Authoring Jailbreak Attacks for Safe Human-LLM Collaborative Writing
- Multilingual Training and Evaluation Resources for Vision-Language Models
- Rethinking Meeting Effectiveness: A Benchmark and Framework for Temporal Fine-grained Automatic Meeting Effectiveness Evaluation
- VERITAS: A Multi-Agent Co-Scientist for Verifiable Image-Derived Hypothesis Testing
- BareBones: Benchmarking Zero-Shot Geometric Comprehension in VLMs
- Text-Guided 6D Object Pose Rearrangement via Closed-Loop VLM Agents
- WebSP-Eval: Evaluating Web Agents on Website Security and Privacy Tasks
- OpenWorldLib: A Unified Codebase and Definition of Advanced World Models
- Automated Conjecture Resolution with Formal Verification
- An Empirical Study of Many-Shot In-Context Learning for Machine Translation of Low-Resource Languages
- HumorRank: A Tournament-Based Leaderboard for Evaluating Humor Generation in Large Language Models
- Internalized Reasoning for Long-Context Visual Document Understanding
- Understand and Accelerate Memory Processing Pipeline for Large Language Model Inference
- Towards Efficient Large Language Reasoning Models via Extreme-Ratio Chain-of-Thought Compression
- Video-OPD: Efficient Post-Training of Multimodal Large Language Models for Temporal Video Grounding via On-Policy Distillation
- SciHorizon-GENE: Benchmarking LLM for Life Sciences Inference from Gene Knowledge to Functional Understanding
- High-Entropy Tokens as Multimodal Failure Points in Vision-Language Models
- FieldWorkArena: Agentic AI Benchmark for Real Field Work Tasks