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.
super 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%).
964
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
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
-
The Salami Slicing Threat: Exploiting Cumulative Risks in LLM Systems
Salami Attack chains low-risk inputs to cumulatively trigger high-risk LLM behaviors, achieving over 90% success on GPT-4o and Gemini while resisting some defenses.
-
Erasing Thousands of Concepts: Towards Scalable and Practical Concept Erasure for Text-to-Image Diffusion Models
ETC scales concept erasure to thousands of concepts in T2I diffusion models via tMM modeling, affine optimal transport, and a robust MoEraser module.
-
Enhancing Fine-Grained Spatial Grounding in 3D CT Report Generation via Discriminative Guidance
DCP-PD improves macro F1 scores on CT report generation benchmarks and introduces a hierarchical location-aware evaluation protocol that reveals ongoing challenges in pathology spatial grounding.
-
ASPIRin: Action Space Projection for Interactivity-Optimized Reinforcement Learning in Full-Duplex Speech Language Models
ASPIRin decouples speaking timing from token content via binary action space projection and applies GRPO with rule-based rewards to optimize interactivity in SLMs without semantic collapse or repetition.
-
Counting to Four is still a Chore for VLMs
VLMs fail at counting because visual evidence degrades in later language layers, and a lightweight Modality Attention Share intervention can encourage better use of image information during answer generation.
-
GRM: Utility-Aware Jailbreak Attacks on Audio LLMs via Gradient-Ratio Masking
GRM ranks Mel bands by attack contribution versus utility sensitivity, perturbs a subset, and learns a universal perturbation to reach 88.46% average jailbreak success rate with improved attack-utility trade-off on four audio LLMs.
-
TensorHub: Scalable and Elastic Weight Transfer for LLM RL Training
TensorHub uses Reference-Oriented Storage to enable scalable weight transfer in LLM RL training by referencing replicated GPU weights, achieving up to 19x reduction in cross-datacenter stall time.
-
Noise-Aware In-Context Learning for Hallucination Mitigation in ALLMs
NAICL reduces hallucination rates in ALLMs from 26.53% to 16.98% via noise priors in context and introduces the Clotho-1K benchmark with four hallucination types.
-
Visually-grounded Humanoid Agents
A coupled world-agent framework uses 3D Gaussian reconstruction and first-person RGB-D perception with iterative planning to enable goal-directed, collision-avoiding humanoid behavior in novel reconstructed scenes.
-
LAMP: Lift Image-Editing as General 3D Priors for Open-world Manipulation
LAMP extracts continuous 3D inter-object transformations from image editing to serve as geometry-aware priors for zero-shot open-world robotic manipulation.
-
When to Trust Tools? Adaptive Tool Trust Calibration For Tool-Integrated Math Reasoning
ATTC reduces 'Tool Ignored' errors in tool-integrated reasoning by adaptively trusting tool results according to generated code confidence, yielding 4.1-7.5% gains across models and datasets.
-
ACF: A Collaborative Framework for Agent Covert Communication under Cognitive Asymmetry
ACF structurally decouples covert communication from semantic reasoning in agent networks using a shared steganographic configuration to maintain performance under cognitive asymmetry.
-
Behavior-Aware Item Modeling via Dynamic Procedural Solution Representations for Knowledge Tracing
BAIM enriches knowledge tracing item representations by deriving stage-level embeddings from Polya's four problem-solving stages and routing them adaptively per learner context, yielding consistent gains over pretraining baselines on two datasets.
-
3DrawAgent: Teaching LLM to Draw in 3D with Early Contrastive Experience
3DrawAgent lets LLMs create complex 3D sketches from text prompts by using pairwise comparisons of their own outputs to self-improve spatial drawing skills without parameter updates.
-
MONETA: Multimodal Industry Classification through Geographic Information with Multi Agent Systems
MONETA is the first multimodal benchmark for industry classification using text and geographic sources, with MLLM baselines at 62-74% accuracy and up to 22.8% gains from multi-turn context enrichment and explanations.
-
TSUBASA: Improving Long-Horizon Personalization via Evolving Memory and Self-Learning with Context Distillation
TSUBASA improves long-horizon personalization in LLMs via dynamic memory evolution for writing and context-distillation self-learning for reading, outperforming Mem0 and Memory-R1 on Qwen-3 benchmarks while reducing token use.
-
LPM 1.0: Video-based Character Performance Model
LPM 1.0 generates infinite-length, identity-stable, real-time audio-visual conversational performances for single characters using a distilled causal diffusion transformer and a new benchmark.
-
MoE Routing Testbed: Studying Expert Specialization and Routing Behavior at Small Scale
A new testbed for MoE models uses domain-based ideal routing as benchmark to quantify expert specialization and compare routing methods at small scale.
-
Walk the Talk: Bridging the Reasoning-Action Gap for Thinking with Images via Multimodal Agentic Policy Optimization
MAPO improves multimodal chain-of-thought reasoning by requiring explicit textual descriptions of visual tool results and using a novel advantage estimator that combines semantic alignment with task rewards.
-
PhysHead: Simulation-Ready Gaussian Head Avatars
PhysHead builds simulation-ready head avatars by layering 3D Gaussians on a head mesh and physics-simulatable hair strands, enabling wind-blown and expression-driven hair motion from video data.
-
SELFDOUBT: Uncertainty Quantification for Reasoning LLMs via the Hedge-to-Verify Ratio
SELFDOUBT introduces the Hedge-to-Verify Ratio from reasoning traces as a single-pass uncertainty signal, with no-hedge traces correct 96% of the time and outperforming semantic entropy at 10x lower cost.
-
Scientific Graphics Program Synthesis via Dual Self-Consistency Reinforcement Learning
SciTikZer-8B uses a new dataset, benchmark, and dual self-consistency RL to generate TikZ code for scientific graphics, outperforming much larger models like Gemini-2.5-Pro.
-
Let Geometry GUIDE: Layer-wise Unrolling of Geometric Priors in Multimodal LLMs
GUIDE unrolls multi-granularity geometric priors layer-wise into early MLLM layers with gating to improve spatial reasoning and perception.
-
FunRec: Reconstructing Functional 3D Scenes from Egocentric Interaction Videos
FunRec reconstructs interactable 3D scenes with articulated parts from in-the-wild egocentric interaction videos, automatically discovering parts, estimating kinematics, and producing simulation-compatible meshes with large gains over prior methods.
-
Content Fuzzing for Escaping Information Cocoons on Digital Social Media
ContentFuzz rewrites posts with LLM guidance from stance model confidence to flip machine labels without altering human intent, tested across four models and three datasets in two languages.
-
VideoStir: Understanding Long Videos via Spatio-Temporally Structured and Intent-Aware RAG
VideoStir introduces a spatio-temporal graph-based structure and intent-aware retrieval for long-video RAG, achieving competitive performance with SOTA methods via a new IR-600K dataset.
-
Watch Before You Answer: Learning from Visually Grounded Post-Training
Filtering post-training data to visually grounded questions improves VLM video understanding performance by up to 6.2 points using 69% of the data.
-
SpatialEdit: Benchmarking Fine-Grained Image Spatial Editing
SpatialEdit provides a benchmark, large synthetic dataset, and baseline model for precise object and camera spatial manipulations in images, with the model beating priors on spatial editing.
-
FileGram: Grounding Agent Personalization in File-System Behavioral Traces
FileGram grounds AI agent personalization in file-system behavioral traces via a data simulation engine, a diagnostic benchmark, and a bottom-up memory architecture.
-
Quantifying Trust: Financial Risk Management for Trustworthy AI Agents
The paper introduces the Agentic Risk Standard (ARS) as a payment settlement framework that delivers predefined compensation for AI agent execution failures, misalignment, or unintended outcomes.
-
Context Matters: Evaluating Context Strategies for Automated ADR Generation Using LLMs
A small recency window of 3-5 prior ADRs as context produces higher-fidelity LLM-generated Architecture Decision Records than no context, full history, or retrieval-augmented selection in typical sequential workflows.
-
ITIScore: An Image-to-Text-to-Image Rating Framework for the Image Captioning Ability of MLLMs
ITIScore evaluates MLLM image captions via image-to-text-to-image reconstruction consistency and aligns with human judgments on a new 40K-caption benchmark.
-
TABQAWORLD: Optimizing Multimodal Reasoning for Multi-Turn Table Question Answering
TABQAWORLD improves multi-turn table QA by dynamically selecting multimodal representations and optimizing reasoning trajectories with metadata, delivering 4.87% accuracy gains over baselines and 33.35% latency reduction.
-
Chart-RL: Policy Optimization Reinforcement Learning for Enhanced Visual Reasoning in Chart Question Answering with Vision Language Models
Chart-RL uses RL policy optimization and LoRA to boost VLM chart reasoning, enabling a 4B model to reach 0.634 accuracy versus 0.580 for an 8B model with lower latency.
-
Beyond Precision: Importance-Aware Recall for Factuality Evaluation in Long-Form LLM Generation
An importance-aware recall metric for LLM factuality evaluation reveals models are better at avoiding false claims than covering all relevant facts.
-
NeuReasoner: Towards Explainable, Controllable, and Unified Reasoning via Mixture-of-Neurons
NeuReasoner detects neuron fluctuation patterns linked to reasoning failures and inserts special tokens to enable controllable self-correction, delivering up to 27% performance gains and 19-63% lower token use across multiple benchmarks and model sizes.
-
InstructTable: Improving Table Structure Recognition Through Instructions
InstructTable combines instruction-guided pre-training on structural patterns with visual fine-tuning and a template-free synthetic data generator (TME) to reach state-of-the-art table structure recognition on public benchmarks and a new complex-table test set.
-
Differential Mental Disorder Detection with Psychology-Inspired Multimodal Stimuli
Introduces the MMH dataset collected via psychology-inspired multimodal stimuli and a paradigm-aware framework that uses inter-disorder prior knowledge as prompts, outperforming baselines on differential detection of depression, anxiety and schizophrenia.
-
CharTool: Tool-Integrated Visual Reasoning for Chart Understanding
CharTool equips MLLMs with cropping and code tools plus agentic RL on DuoChart data to raise chart-reasoning accuracy by up to 9.78 percent on benchmarks.
-
Rethinking Language Model Scaling under Transferable Hypersphere Optimization
HyperP transfers optimal learning rates across model width, depth, tokens, and MoE granularity under Frobenius-sphere constraints, delivering stable scaling and 1.58x efficiency gains.
-
SpatialStack: Layered Geometry-Language Fusion for 3D VLM Spatial Reasoning
SpatialStack improves 3D spatial reasoning in vision-language models by stacking and synchronizing multi-level geometric features with the language backbone.
-
Structured Visual Narratives Undermine Safety Alignment in Multimodal Large Language Models
Comic-based visual narratives achieve over 90% ensemble success rates on multiple MLLMs, outperforming text and random-image baselines while breaking existing safety methods and evaluators.
-
PersonaVLM: Long-Term Personalized Multimodal LLMs
PersonaVLM adds memory extraction, multi-turn retrieval-based reasoning, and personality inference to multimodal LLMs, yielding 22.4% gains on a new long-term personalization benchmark and outperforming GPT-4o.
-
Cognitive Mismatch in Multimodal Large Language Models for Discrete Symbol Understanding
MLLMs exhibit a consistent recognition-reasoning inversion on discrete visual symbols across domains, underperforming on elementary perception while appearing competent on higher-level reasoning via linguistic compensation.
-
Towards Safer Large Reasoning Models by Promoting Safety Decision-Making before Chain-of-Thought Generation
Safety degradation in large reasoning models occurs only after chain-of-thought is enabled; adding pre-CoT safety signals from a BERT classifier on safe models improves safety while preserving reasoning ability.
-
AdaQE-CG: Adaptive Query Expansion for Web-Scale Generative AI Model and Data Card Generation
AdaQE-CG uses context-aware adaptive query expansion and inter-card knowledge transfer from a MetaGAI Pool to generate higher-quality model and data cards than prior methods, validated on the new expert-annotated MetaGAI-Bench.
-
Logics-Parsing-Omni Technical Report
Omni Parsing framework converts complex multimodal signals into locatable, enumerable, and traceable structured knowledge via hierarchical detection, recognition, and interpreting with strict evidence alignment.
-
MICA: Multi-granularity Intertemporal Credit Assignment for Long-Horizon Emotional Support Dialogue
MICA combines incremental per-turn distance rewards and Monte Carlo returns from a shared potential function over user support states to create a mixed advantage signal that enables stable multi-turn RL optimization for emotional support dialogues.
-
CRISP: Compressed Reasoning via Iterative Self-Policy Distillation
CRISP achieves 57-59% token reduction on MATH-500 with 9-16 point accuracy gains on Qwen3 models via iterative self-distillation of concise reasoning behavior.
-
TW-Sound580K: A Regional Audio-Text Dataset with Verification-Guided Curation for Localized Audio-Language Modeling
TW-Sound580K dataset plus Tai-LALM model with dynamic Dual-ASR arbitration lifts localized Taiwanese audio-language accuracy to 49.1% on the TAU benchmark.