What the smart people are recommending. 7786 books, tools, and products endorsed by the thinkers absorb.md tracks. Ranked by how many times each has been recommended across compiled podcasts, papers, posts, and tweets.
“The full simulation codebase and FPGA estimation scripts are publicly available at https://github.com/therealdeadbeef/aerospace-fl-quantization.”
“We present results of our method using the TabPFN-TS backbone and compare performance with the current state of the art tabular methods.”
“Code is available at: https://github.com/czg1225/DMax”
“EgoEverything is a benchmark that explicitly considers human behavior by leveraging human attention signals, abstracted from gaze data, when generating questions. It comprises over 5,000 multiple choi…”
“We propose a new method, Multiple Embedding Replay Selection, MERS, which replaces the buffer selection module with a graph-based approach that integrates both supervised and self-supervised embedding…”
“In this paper, we introduce HistDiT, a novel latent conditional Diffusion Transformer (DiT) architecture that establishes a new benchmark for visual fidelity in virtual histological staining.”
“We propose Long-Term Embeddings (LTE) as a high-inertia contextual anchor to bridge this gap.”
“We present STEP-Parts, a deterministic CAD-to-supervision toolchain that extracts geometric instance partitions directly from raw STEP B-Reps and transfers them to tessellated carriers through retaine…”
“Three small frozen models (Llama-3.2-1B, Qwen2.5-1.5B, Gemma-2-2B) encode the input into a shared latent space whose aggregate signal is injected into two larger frozen models (Phi-3-mini, Mistral-7B)…”
“Three small frozen models (Llama-3.2-1B, Qwen2.5-1.5B, Gemma-2-2B) encode the input into a shared latent space whose aggregate signal is injected into two larger frozen models (Phi-3-mini, Mistral-7B)…”
“Three small frozen models (Llama-3.2-1B, Qwen2.5-1.5B, Gemma-2-2B) encode the input into a shared latent space whose aggregate signal is injected into two larger frozen models (Phi-3-mini, Mistral-7B)…”
“Two larger frozen models (Phi-3-mini, Mistral-7B), whose representations feed a lightweight cross-attention output node.”
“Two larger frozen models (Phi-3-mini, Mistral-7B), whose representations feed a lightweight cross-attention output node.”
“sudo add-apt-repository ppa:inkscape.dev/trunk; sudo apt-get install inkscape-trunk”
“sudo curl -L https://github.com/yt-dlp/yt-dlp/releases/latest/download/yt-dlp -o /usr/local/bin/yt-dlp”
“curl https://sh.rustup.rs -sSf | sh”
“sudo apt install signal-desktop”
“sudo apt-get install -y keepassxc”
“sudo apt-get install -y yubikey-manager yubikey-personalization-gui”
“curl -L https://download.jetbrains.com/webide/PhpStorm-2021.3.1.tar.gz”
“You could make that install via composer as well. In general, converting stuff to a composer-based approach might be a good idea.”
“Ever considered switching to something simple like handlebars?”
“Lots of CSS as well, maybe LESS/SCSS/SASS should be considered to make these easier to manage.”
“Lots of CSS as well, maybe LESS/SCSS/SASS should be considered to make these easier to manage.”
“Lots of CSS as well, maybe LESS/SCSS/SASS should be considered to make these easier to manage.”
“There's a number of png files in this, have those been run through pngcrush? (Seems like nope.)”
“the local hangout spot of course was Panera Bread”
“Apply for Apple Card in the Wallet app to see your credit limit offer in minutes.”
“if you want something just as cool for your team, Vistaprint offers everything you need... get the best apparel for your business at Vistaprint... Right now, new customers get 20% off with code NEW20 …”
“how Colin Engel set out to make robots part of our daily lives and brought us one of the most iconic home helpers ever, the Roomba.”
“It came out in 1999 and called My Real Baby, and we sold 150,000 of them... we learned how to make low-cost robots.”
“we started going down to Washington with our PacBot robot... you got to send this to Afghanistan.”
“Extensive evaluations demonstrate that our resulting model, Metis, reduces tool invocations by orders of magnitude while simultaneously elevating reasoning accuracy.”
“To address this, we introduce SIM1, a physics-aligned real-to-sim-to-real data engine that grounds simulation in the physical world.”
“We introduce RewardFlow, an inversion-free framework that steers pretrained diffusion and flow-matching models at inference time through multi-reward Langevin dynamics.”
“We propose Pearl (Predictive Embedding Alignment for Reasoning in Latent space), a JEPA-inspired framework that learns from expert tool-use trajectories entirely in the latent space, eliminating the n…”
“Overall, these results demonstrate that task-oriented, region-specific training substantially improves detection performance in acoustically complex tropical environments, and highlight the potential …”
“We introduce LINE, a novel, training-free iterative approach tailored for open-vocabulary concept labeling in vision models.”
“We propose OV-Stitcher, a training-free framework that addresses this limitation by stitching fragmented sub-image features directly within the final encoder block.”
“Therefore, we propose HST-HGN, a novel Heterogeneous Spatial-Temporal Hypergraph Network driven by Bidirectional State Space Models.”
“we study the applicability of Conditional Neural Processes (CNP) to the task of self-supervised multimodal action prediction in robotics.”
“We find a good MNS-inspired model in the existing Deep Modality Blending Network (DMBN), able to reconstruct the visuo-motor sensory signal during a partially observed action sequence by leveraging th…”
“Therefore, we propose a revised version, termed DMBN-Positional Time Encoding (DMBN-PTE), that facilitates learning a more robust representation of temporal information, and provide preliminary result…”
“Multimodal reasoning models (MRMs) trained with reinforcement learning with verifiable rewards (RLVR) show improved accuracy on visual reasoning benchmarks.”
“We systematically study this phenomenon across seven challenging real-world spatial reasoning benchmarks and find that it affects contemporary MRMs such as ViGoRL-Spatial, TreeVGR as well as our own m…”
“We systematically study this phenomenon across seven challenging real-world spatial reasoning benchmarks and find that it affects contemporary MRMs such as ViGoRL-Spatial, TreeVGR as well as our own m…”
“We systematically study this phenomenon across seven challenging real-world spatial reasoning benchmarks and find that it affects contemporary MRMs such as ViGoRL-Spatial, TreeVGR as well as our own m…”
“To address this, we propose Faithful GRPO (FGRPO), a variant of GRPO that enforces consistency and grounding as constraints via Lagrangian dual ascent.”
“We evaluate FGRPO on Qwen2.5-VL-7B and 3B backbones across seven spatial datasets.”
“The CrashSight benchmark, including the full dataset and code, is accessible at https://mcgrche.github.io/crashsight.”
“To address this, we propose OVS-DINO, a novel framework that revitalizes latent edge-sensitivity of DINO through structural alignment with the Segment Anything Model (SAM).”
“We introduce KnowU-Bench, an online benchmark for personalized mobile agents built on a reproducible Android emulation environment”
“First, we release MiniF2F-Hard and FIMO-Hard, expert-reannotated Hard Mode variants of two widely-used ATP benchmarks.”
“We evaluate six CAM techniques: GradCAM, GradCAM++, LayerCAM, EigenCAM, ScoreCAM, and MS GradCAM++ across three CNN architectures (DenseNet201, InceptionV3, ResNet50V2) over thirty training epochs on …”
“We evaluate six CAM techniques: GradCAM, GradCAM++, LayerCAM, EigenCAM, ScoreCAM, and MS GradCAM++ across three CNN architectures (DenseNet201, InceptionV3, ResNet50V2) over thirty training epochs on …”
“We evaluate six CAM techniques: GradCAM, GradCAM++, LayerCAM, EigenCAM, ScoreCAM, and MS GradCAM++ across three CNN architectures (DenseNet201, InceptionV3, ResNet50V2) over thirty training epochs on …”
“We evaluate six CAM techniques: GradCAM, GradCAM++, LayerCAM, EigenCAM, ScoreCAM, and MS GradCAM++ across three CNN architectures (DenseNet201, InceptionV3, ResNet50V2) over thirty training epochs on …”
“We evaluate six CAM techniques: GradCAM, GradCAM++, LayerCAM, EigenCAM, ScoreCAM, and MS GradCAM++ across three CNN architectures (DenseNet201, InceptionV3, ResNet50V2) over thirty training epochs on …”
“We evaluate six CAM techniques: GradCAM, GradCAM++, LayerCAM, EigenCAM, ScoreCAM, and MS GradCAM++ across three CNN architectures (DenseNet201, InceptionV3, ResNet50V2) over thirty training epochs on …”
“We propose a significantly more generalized approach, replacing discrete latent variables with natural language conditioning via a text-conditioned Variational Autoencoder (VAE). Our core innovation u…”
“We introduce InstAP, an Instance-Aware Pre-training framework that jointly optimizes global vision-text alignment and fine-grained, instance-level contrastive alignment by grounding textual mentions t…”
“To support this, we present InstVL, a large-scale dataset (2 million images, 50,000 videos) with dual-granularity annotations: holistic scene captions and dense, grounded instance descriptions.”
“Second, to address this gap, we introduce Phantasia, a context-adaptive backdoor attack that dynamically aligns its poisoned outputs with the semantics of each input.”
“We propose \textbf{TASU2}, a controllable CTC simulation framework that simulates CTC posterior distributions under a specified WER range, producing text-derived supervision that better matches the ac…”
“The code and benchmark will be available on GitHub.”
“SNIP (Meidani et al., 2024), a contrastive pre-training model inspired by CLIP, advances LSO by introducing a multi-modal approach: aligning symbolic and numeric encoders in a shared latent space to l…”
“To bridge this gap, we introduce ProMedical, a unified alignment framework grounded in fine-grained clinical criteria.”
“We publicly release our datasets, reward models, and benchmarks to facilitate reproducible research in safety-aware medical alignment.”
“We publicly release our datasets, reward models, and benchmarks to facilitate reproducible research in safety-aware medical alignment.”
“The MATLAB code used in the numerical experiments is also made freely available to support the reproducibility of the results.”
“To sort this problem out, we propose a variational restricted maximum likelihood (VREML) framework that approximates the intractable marginal likelihood using a Gaussian variational distribution.”
“To address these issues, we combine the elastic net loss with a robust loss framework to construct a sparse $\varepsilon$-insensitive bounded asymmetric elastic net loss, and integrate it with SVM to …”
“Existing support vector machines(SVM) models are sensitive to noise and lack sparsity, which limits their performance. To address these issues, we combine the elastic net loss with a robust loss frame…”
“To address these issues, we combine the elastic net loss with a robust loss framework to construct a sparse $\varepsilon$-insensitive bounded asymmetric elastic net loss, and integrate it with SVM to …”
“This paper reframes annotation as a measurement process and introduces a statistical framework for decomposing labeling outcomes into interpretable sources of variation: instance difficulty, annotator…”
“In this paper, we propose a Newton-Schulz-based Riemannian Gradient Scheme (NS-RGS) for orthogonal group synchronization that significantly reduces computational cost by replacing the SVD or QR step w…”
“See project page: https://github.com/ARC0127/Fisher-Decorator.”
“In symmetric binary Gaussian mixtures, the criterion recovers the critical diffusion time detected by the midpoint derivative of the score and agrees with the spectral criterion of Biroli, Bonnaire, d…”
“Experiments on realistic genome-wide association study data confirm that VD-T-Rex controls FDR and achieves power at scales where all competing methods either fail or time out.”
“She is a professor of engineering at Olin College and the author of the book, How Infrastructure Works Inside the Systems That Shape Our World.”
“The study examined cultural norms in over 30 countries around the world, and it became the basis for Michelle's book, Rulemakers, Rule Breakers, How Tight and Loose Cultures Wire Our World.”
“He's the author of Walkable City, How Downtown Can Save America One Step at a Time.”
“_Blog post by Sam Bankman-Fried_ https://sambf.substack.com/p/ftx-pre-mortem-overview”
“N2, is now the number one most downloaded human robotics model in the world.”
“I think that if somebody else is using your prompts, they're still not going to necessarily make the same work?... but I still think the client still going to be hiring Design Army and many of great f…”
“That's why Veeam is introducing Agent Commander, the first solution to detect, protect, and precisely undo AI mistakes.”
“I am currently the chairman of the board of the One Club for Creativity, and I have been on the board for 13 years.”
“Because we're proud to be invested in America. See how at USPMI.com.”
“Morgan Stanley is here to help with their podcast, Thoughts on the Market. it. Thoughts on the Market is your daily market snapshot, covering trends across the global investment landscape and offering…”
“Some people use iMessage”
“So nano triple is literally all it does is it pulls in your Gemini API key and it always gives you three nano banana images every time you make an image request.”
“I would recommend people to try Amazon Grocery because it's quite cheap. And you can now get it within an hour or two delivered to your house.”
“I asked in the Substack chat, which people should join. It's completely free. Link is in the show notes.”
“I shared this insight in a special deep dive report to subscribers of my research service, Value Spotlight. The report is called A Generational Moment, Reigniting Human Connections Through a Tangible …”
“you know one fairy tale that I think is or fable that is useful is the boy who cried wolf”
“Did you read the Ronan Farrow piece in The New Yorker about Sam Altman?”
“I want to start with a video game that I liked to play during the pandemic called Overcooked.”
“We benchmark eight state-of-the-art VAD methods on AnoVox, the largest synthetic dataset for anomaly detection in autonomous driving.”
“https://about.fb.com/news/2024/08/why-europe-should-embrace-open-source-ai-zuckerberg-ek”
“# Open Source AI is the Path Forward”