sonnet

Our most intelligent workhorse model yet for coding and agents has arrived ⚡ Meet Gemini 3.7 Flash. — Crush that seemingly endless to-do list. Gemini Spark in the @geminiapp now uses 3.7 Flash. The ne

Our most intelligent workhorse model yet for coding and agents has arrived ⚡ Meet Gemini 3.7 Flash. — Crush that seemingly endless to-do list. Gemini Spark in the @geminiapp now uses 3.7 Flash. The new model can equip your personal AI agent to work even smarter for you by https://t.co/hgM1xWiyvI

Gemini 3.7 Flash is here. It’s stronger for coding, knowledge work, and web development. 🧵 https://t.co/Yzc5ViW5Di

We sat down with Apollo 2 to talk about what it's really like running on Gemini Robotics 2. 🤖 https://t.co/PhxXMkMfBY

Predicting cyclones accurately can help save lives - and every hour of lead time counts. Published in @Nature, our AI model WeatherNext achieves state-of-the-art accuracy in forecasting a storm’s trac

Predicting cyclones accurately can help save lives - and every hour of lead time counts. Published in @Nature, our AI model WeatherNext achieves state-of-the-art accuracy in forecasting a storm’s track and intensity, giving us a critical extra 24 hours to prepare on average. 🧵 https://t.co/Noht1k1Zl7

Multimodal Model Diffing for Feature Discovery and Control

Multimodal Large Language Models (MLLMs) exhibit strong visual understanding, yet the internal features that cause these behaviors remain difficult to identify, audit, or control. While applicable to post-hoc inspection, hidden states that are decomposed into interpretable feature directions using sparse autoencoders (SAEs) neither readily isolate which features are changed by multimodal training, nor are they directly useful for targeted control. We introduce MMDiff, a multimodal model-diffing framework that trains multimodal SAEs and turns them into feature-level interfaces for discovering and controlling multimodal behavior. MMDiff supports three uses: (i) feature isolation, by diffing a base-LM SAE against its multimodal-adapted counterpart to identify features altered by multimodal training; (ii) task-specific feature detection, via per-token contrastive firing analysis that isolates causal features; and (iii) feature-level control, by causally removing or steering the discovered feature directions. We train multimodal SAEs for three MLLM families, LLaVA-MORE, PaliGemma 2, and InternVL3.5, and evaluate on visual-spatial understanding, multimodal safety, and OCR. MMDiff discovers sparse, causally specific features whose removal selectively degrades target behaviors by an average of 12% on spatial tasks and 17% on OCR, and reduces attack success rate by 24% on multimodal safety attacks, with no impact on VQA performance. Steering these features improves spatial and OCR accuracy by +3.6% and +1.8% on average over a standard single-layer steering baseline. These results show that multimodal SAEs can serve not only as interpretability tools, but as mechanisms for auditing, steering, and controlling MLLMs behavior toward safer and more capable generations.

Multi-Agent Forensic Reasoning for Generalizable Deepfake Video Detection

The malicious use of generative artificial intelligence to create highly realistic deepfake videos raises serious ethical concerns and poses substantial challenges to AI safety. However, existing deepfake video benchmarks provide limited coverage of recent synthesis methods and generally lack reliable fine-grained textual annotations. Meanwhile, conventional detectors and multimodal large language models (MLLMs), whether operating as a single model or relying on a single analytical perspective, often fail to capture subtle forgery artifacts, limiting their generalization to emerging AI-generated methods. To address these limitations, we introduce FaceVid-Forensics-100K, a large-scale deepfake video dataset comprising 100,000 videos and spanning 33 synthesis methods across face swapping, face reenactment, and entire-face synthesis, including recent generators such as Seedance 2.0. The dataset provides fine-grained textual annotations of visual observations and verdict-consistent forensic explanations, automatically synthesized through a multi-model aggregation and conflict-resolution pipeline powered by advanced MLLMs. Building on this benchmark, we propose a multi-agent forensic reasoning framework that employs four specialized domain-expert agents to independently analyze forgery cues from four perspectives: texture, lighting, motion, and physics. A judge agent then reconciles their reports to produce a final prediction together with an explanation. Extensive evaluations on out-of-domain test sets show that, despite being composed entirely of small open-source MLLMs, our framework outperforms all methods including closed-source GPT and Gemini models and ranks first across all reported metrics on this benchmark. The project page is available at https://xavierjiezou.github.io/ARGUS/.

Energy-Guided Flow Matching

Pixel-space generative models bypass lossy latent compression, yet necessitate joint learning of global structure and fine-grained details in a high-dimensional space. Standard flow matching interpolates noise toward a fixed clean-image endpoint, leaving the spectral evolution to be learned implicitly. In this paper, we introduce Energy-Guided Flow Matching(EG-FM) that explicitly models a coarse-to-fine generative trajectory by moving endpoint. Specifically, EG-FM replaces the fixed endpoint with a heat-kernel-filtered endpoint that evolves smoothly from low-frequency image to clean image. The fraction of high-frequency signal in moving endpoint is released by an image-specific energy-guided scheduling, leading to the re-targeting of velocity in flow matching. Our framework requires no adaptation of the backbone and training data, bringing negligible cost on the training and inference stages. In our experiment, EG-FM consistently achieves lower FID on the ImageNet class-conditional image generation task at 256 times 256 with fewer epochs, reaching an FID of 1.55 at 200 epochs and 1.45 at 600 epochs. We continue training the generation task on the setting of 512 times 512 resolution, yielding a FID of 1.58 after only 40 high-resolution adaptation epochs. Furthermore, we transfer EG-FM on text-to-image generation and achieve 0.85 on GenEval score and 83.9 on DPG-Bench. Code is available at https://github.com/ysng123/EG-FM.

Invisible Shortcuts: Why Vision Encoders Know Your Camera

Deep vision models exploit shortcuts, relying on cues that correlate with supervision signals. Prior work has focused on visible biases, such as object-background or texture correlations. We identify a different source of shortcut learning: invisible metadata traces embedded at the pixel level, for metadata such as image processing and photo acquisition. We hypothesize that large-scale semantic supervision, whether through categorical labels (ImageNet) or billion-scale captions (LAION), naturally induces metadata-semantics correlations during pretraining, leading models to convert low-level signals into predictive features. By introducing controlled metadata-semantics correlations, we show that stronger ones produce systematically higher sensitivity to metadata traces and larger performance degradation under metadata distribution shifts. We further explore mitigation strategies applied during and after pretraining that reduce sensitivity not only to targeted metadata but also to unseen ones, without sacrificing performance on downstream tasks. Metadata sensitivity also has a positive side: it partly explains the strong generated-image detection ability of some encoders, while its mitigation can improve out-of-distribution generalization. Code: https://github.com/ryan-caesar-ramos/visual-encoder-traces

Claude-3.5-Sonnet-20241022 - LiveCodeBench

LiveCodeBench pass@1 48.7 across 1055 tasks

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-sonnet-4-5 - SWE-Bench Verified

SWE-Bench Verified resolved rate 74.8

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5

claude-3-5-sonnet — LiveBench Scores

language: 0.5 | coding: 0.0 | instruction_following: 1.0 | Overall: 0.5