media Analytics Vidhya · 502d ago

Google DeepMind releases Gemini 2.5 Pro experimental model

from English

Google DeepMind has unveiled the Gemini 2.5 Pro (experimental) model, which ranks #1 on the LMArena Leaderboard and is available for free on Google AI Studio.

The model features enhanced multimodal capabilities, including support for text documents, YouTube video links, external files, camera input, and audio clips.
It achieves a score of 84% on GPQA Diamond and 18.8% on Humanity’s Last Exam, outperforming models like GPT-4.5 and Claude 3.7 Sonnet in specific benchmarks.
Google plans to make the model available on Vertex AI and launch an improved version supporting a context window of 2 million tokens.

Importance 3/3 Beats a top-lab benchmark Analytics Vidhya Google DeepMind Multimodal Reasoning models

Benchmarks

Benchmark	Model	Score
AIME 2025	Gemini 2.5 Pro (experimental)	86.7%
GPQA Diamond	Gemini 2.5 Pro (experimental)	84%
Humanity's Last Exam	Gemini 2.5 Pro (experimental)	18.8%

Read original

arxiv arXiv cs.AI · 51d ago · 2 views

Dual-Agent Framework for Cross-Model Verified Translation

A dual-agent framework converts natural-language experiment protocols into executable commands for robotic lab platforms. It uses a Parser Agent and a rule-based mapping engine to translate protocols, with a heterogeneous LLM Validation Agent ensuring accuracy and triggering self-correction. The framework successfully enables end-to-end autonomous execution of microplate-based experiments like the Bradford assay.

arxiv arXiv cs.AI · 51d ago

Lagrange: Open-Vocabulary Sparse Framework for End-to-End Driving

Lagrange introduces an open-vocabulary, energy-based sparse framework for generalized end-to-end driving. It uses Vision-Language Models to generate class-agnostic object proposals and encodes them into continuous semantic tokens, enabling robust generalization to anomalous scenarios while adhering to vehicle kinematics through Lagrangian action minimization.

arxiv arXiv cs.LG · 51d ago · 1 view

Pose6DAug: Physically Plausible Multi-view Object Swapping

Pose6DAug enables robot data augmentation by swapping objects in successful episodes while preserving physically valid 6D pose trajectories. It operates in 3D using a mesh anchored by temporally coherent poses, ensuring multi-view consistency and physical plausibility. Fine-tuning a VLA policy on this augmented data improves novel object success rates by 16.5% over state-of-the-art baselines.

arxiv arXiv cs.LG · 51d ago

De-biased VLM-as-3D-Judge Protocol for Furniture Generation

A de-biased VLM-based judge protocol specializes TRELLIS on furniture generation using lightweight adaptation. The protocol addresses failure modes like image overload and geometry-hiding, with calibration showing 0.83–1.0 win rates and base-vs-base symmetry at 0.5. Among six adaptation methods, conditioner repair under severe degradation achieves parity with the base model, while no method exceeds a 65% win-rate target.

arxiv arXiv cs.LG · 52d ago · 3 views

OneCanvas: 3D Scene Understanding via Panoramic Reprojection

OneCanvas enables 3D scene understanding in Vision-Language Models by aggregating patch features onto a single panoramic canvas using 3D world coordinates. It achieves state-of-the-art performance on SQA3D and VSI-Bench, and generalizes to out-of-distribution data on SPBench, using significantly less training compute than existing methods.