Search: “models”

A user reports that Opus 4.7 performs better in Claude Code when executed with a minimal system prompt (using just a period) rather than the full default system prompt, suggesting that reducing system

arXiv:2604.16220v1 Announce Type: new Abstract: In computer vision and machine learning for geographic data, out-of-domain generalization is a pervasive challenge, arising from uneven global data cove

arXiv:2604.15645v1 Announce Type: new Abstract: We present PINNACLE, an open-source computational framework for physics-informed neural networks (PINNs) that integrates modern training strategies, mul

arXiv:2604.15830v1 Announce Type: new Abstract: Reinforcement learning has become a powerful approach for enhancing large language model reasoning, but faces a fundamental dilemma: training on easy pr

arXiv:2604.16108v1 Announce Type: new Abstract: Speech-Driven Facial Animation (SDFA) has gained significant attention due to its applications in movies, video games, and virtual reality. However, mos

arXiv:2604.15411v1 Announce Type: cross Abstract: The paradigm of agentic science requires AI systems to conduct robust reasoning and engage in long-horizon, autonomous exploration. However, current s

arXiv:2604.15385v1 Announce Type: cross Abstract: Software documentation is essential for program comprehension, developer onboarding, code review, and long-term maintenance. Yet producing quality doc

arXiv:2511.03056v2 Announce Type: replace-cross Abstract: Conversational AI is constrained in many real-world settings where only one side of a dialogue can be recorded, such as telemedicine, call cen

arXiv:2603.13091v2 Announce Type: replace Abstract: The growing interest in embodied agents increases the demand for spatiotemporal video understanding, yet existing benchmarks largely emphasize extra

arXiv:2604.15838v1 Announce Type: new Abstract: Distribution shift severely degrades the performance of deep forecasting models. While this issue is well-studied for individual time series, it remains

arXiv:2503.05578v4 Announce Type: replace Abstract: Pose estimation-guided unseen object 6-DoF robotic manipulation is a key task in robotics. However, the scalability of current pose estimation metho

arXiv:2604.15946v1 Announce Type: new Abstract: Open-vocabulary semantic segmentation enables models to segment objects or image regions beyond fixed class sets, offering flexibility in dynamic enviro

arXiv:2604.16138v1 Announce Type: new Abstract: We present a dataset and a model for sentiment analysis of German sign language (DGS) fairy tales. First, we perform sentiment analysis for three levels

This post discusses advanced rendering techniques for realistic visual effects, including sheer fabric simulation with light transmission properties, cloth physics responsive to wind forces, depth-of-

arXiv:2604.15837v1 Announce Type: new Abstract: Combinatorial black-box optimization in high-dimensional settings demands a careful trade-off between exploiting promising regions of the search space a

arXiv:2604.15559v1 Announce Type: new Abstract: Recent work on subliminal learning demonstrates that language models can transmit semantic traits through data that is semantically unrelated to those t

arXiv:2604.15460v1 Announce Type: cross Abstract: The rapid evolution of Large Language Models (LLMs) has made them powerful tools for enhancing student writing. This study explores the extent and lim

arXiv:2604.15702v1 Announce Type: new Abstract: We introduce a cross-domain behavioural assay of monitoring-control coupling in LLMs, grounded in the Nelson and Narens (1990) metacognitive framework a

arXiv:2604.15344v1 Announce Type: cross Abstract: Large language models (LLMs) are increasingly integrated into design and development workflows, yet decisions about their use are rarely binary or pur

arXiv:2604.15705v1 Announce Type: new Abstract: Reinforcement Fine-Tuning (RFT) has established itself as a critical paradigm for the alignment of Multi-modal Large Language Models (MLLMs) with comple

Noetik uses transformer neural networks and machine learning to improve cancer drug trial success rates, addressing the historically high failure rate (95%) in clinical development. The approach lever

arXiv:2604.15507v1 Announce Type: new Abstract: Planning safe trajectories under model uncertainty is a fundamental challenge. Robust planning ensures safety by considering worst-case realizations, ye

arXiv:2503.07976v2 Announce Type: replace-cross Abstract: This paper investigates approximation capabilities of two-dimensional (2D) deep convolutional neural networks (CNNs), with Korobov functions s

arXiv:2603.05719v2 Announce Type: replace Abstract: Training machine learning models for radioisotope identification using gamma spectroscopy remains an elusive challenge for many practical applicatio

ComfyUI's HY 3D 3.0 nodes enable rapid 3D asset generation from single or multi-view images, producing high-fidelity 3D models suitable for applications including product visualization and game develo

We have been named one of the 40 Most Innovative AI-Native Prosumer Companies by @notablecap. The Prosumer AI 40 recognizes companies building the tools that blur the line between professional and con

🔴 BREAKING Speculative decoding just got real for local LLMs. llama.cpp merged speculative checkpointing (PR #19493). Expect 0-50% speedups on coding tasks with `--spec-type ngram-mod`. This means: •

Just got access to Grok 4.3 and the first thing I did was throw the hardest task I usually run on claude to test it gave it a complex research prompt on deepseek: >thought for 13 mins and 17 seconds >

OMG. Let’s get one thing straight. Claude doesn’t get anxious. It mimics people who get anxious. Those two things are NOT the same. My head is shaking so much I need medical attention. anthropic's in-

This post compares AI assistants' responses to a request about driving to get gas, claiming that Grok 4.3 provides the requested information while ChatGPT, Claude, and Gemini decline or suggest altern

GDPval is one of the most important benchmarks of AI ability because it is based on human expertise. It compares expert human performance to AI performance using expert human judges who spend an avera

I prefer my design tool to be more closely integrated with where my agents work. I spent a few hours building my own design tool (inspired by Claude Design) inside my orchestrator. I can use this with

I think Artificial Analysis does a good job overall and provides transparency in benchmarking, but GDPval-AA is not a good benchmark and needs to stop being reported. It is Gemini 3.1 judging other mo

NEW paper from Apple. Interesting idea: 'Attention to Mamba'. The paper introduces a two-stage recipe for cross-architecture distillation from Transformers into Mamba. Naive distillation collapses tea

A 25,000 budget provides access to quality used electric vehicles, including loaded models like the 2024 Chevrolet Blazer EV LT2 . Used EV market depreciation creates significant deals due to consumer

30K+ likes in the first hour. 🤯 That is crazy! Design is unsolved with agents. But lots of impactful work generated by agents is around design. Claude Design is Anthropic's way of saying that they are

arXiv:2601.07667v2 Announce Type: replace Abstract: Due to the prevalence of large language models (LLMs), key-value (KV) cache reduction for LLM inference has received remarkable attention. Among num

arXiv:2604.14853v1 Announce Type: new Abstract: Test-time compute scaling, the practice of spending extra computation during inference via repeated sampling, search, or extended reasoning, has become

arXiv:2604.15059v1 Announce Type: new Abstract: Motion artifacts present a significant challenge in structural MRI (sMRI), often compromising clinical diagnostics and large-scale automated analysis. W

arXiv:2604.13101v1 Announce Type: cross Abstract: The integration of Large Language Models (LLMs) into aviation safety decision-making represents a significant technological advancement, yet their sta

arXiv:2603.20340v3 Announce Type: replace-cross Abstract: Self-generated skills for web agents are often unstable and can even hurt performance relative to direct acting. We argue that the key bottlen

arXiv:2604.15086v1 Announce Type: cross Abstract: Recent advances in video-to-audio (V2A) generation enable high-quality audio synthesis from visual content, yet achieving robust and fine-grained cont

arXiv:2604.14773v1 Announce Type: new Abstract: While LLMs have demonstrated remarkable potential in Question Answering (QA), evaluating personalization remains a critical bottleneck. Existing paradig

arXiv:2504.16455v2 Announce Type: replace Abstract: Transformer-based networks have achieved strong performance in low-level vision tasks like image deraining by utilizing spatial or channel-wise self

arXiv:2604.14644v1 Announce Type: new Abstract: The inability to filter out in advance all potentially problematic data from the pre-training of large language models has given rise to the need for me

arXiv:2604.14870v1 Announce Type: new Abstract: Local loss-landscape stabilization under sample growth is typically measured either pointwise or through isotropic averaging in the full parameter space