46 articles mentioning seed-1.6-flash
arXiv:2609.02011v1 Announce Type: cross Abstract: Large language model question answering over power-grid models must respect a fixed context budget. We introduce seed-anchored graph rendering, a deterministic method that prioritizes query-local graph evidence without adding method-specific tuned or
arXiv:2609.02499v1 Announce Type: cross Abstract: Recommender-system experiments often rely on a single random training seed, assuming that run-to-run stochasticity has limited impact on evaluation conclusions. This assumption is risky, as a training seed may influence several algorithm-dependent me
arXiv:2609.00844v1 Announce Type: new Abstract: Customer-service QA in an AI contact center (AICC) runs under deployment constraints that benchmark QA misses: tight voice-hotline latency and a high cost for unsupported or wrong automatic answers. We deploy a system that answers only from a closed se
arXiv:2608.29591v1 Announce Type: new Abstract: Users articulate the same advice-seeking request in different ways: some specify detailed constraints, others gesture at a vague need. Prior work treats this variation as noise to be averaged away; we instead treat it as a stable, measurable structure
arXiv:2608.27729v1 Announce Type: new Abstract: Function routing -- selecting the correct API call from a fixed catalog given a natural-language request -- is a deployment problem where small students are attractive but knowledge distillation gains are typically reported single-seed, at scales where
arXiv:2512.12066v3 Announce Type: replace-cross Abstract: Current safety evaluations of large language models rely on single-shot testing, implicitly assuming that model responses are deterministic and representative of the model's safety alignment. We challenge this assumption by investigating the
arXiv:2608.26161v1 Announce Type: cross Abstract: Although Large Language Models (LLMs) demonstrate remarkable capabilities in reasoning and decision-making, high-fidelity probabilistic sampling remains a persistent challenge. When generating random variables, LLMs consistently exhibit systematic bi
arXiv:2608.26743v1 Announce Type: new Abstract: Enterprises fine-tune language models on proprietary data that may later require removal due to privacy, contractual, or compliance obligations. Selective unlearning removes requested knowledge while preserving model utility, offering a practical alter
arXiv:2608.25276v1 Announce Type: new Abstract: Mixture-of-Experts (MoE) architectures enable scalable and efficient large language models (LLMs) by selectively activating expert sub-networks through a routing mechanism. However, this adaptive design introduces a new attack surface: specific experts
arXiv:2607.01153v3 Announce Type: replace-cross Abstract: Safety evaluations for language models increasingly depend on judgments about ambiguous natural-language behaviour: whether a model followed an instruction, refused appropriately, complied with a policy, or misreported progress in an agentic
Since launching last year, the startup today has more than 8 million people using the open source or hosted version of its models, and now generates annual recurring revenue of $21 million.
arXiv:2607.20443v1 Announce Type: new Abstract: We release GLAN-QnA-KR, a 303,581-row openly redistributable Korean instruction-QA corpus produced via the seedless taxonomy-driven GLAN synthesis pipeline with Microsoft's Phi-3.5-MoE-instruct as the producer model (generation: 2024-12; release: 2024-
arXiv:2503.06437v3 Announce Type: replace-cross Abstract: We present SEED (Semantic Evaluation for Visual Brain Decoding), a novel metric for evaluating the semantic decoding performance of visual brain decoding models. It integrates three complementary metrics, each capturing a different aspect of
arXiv:2607.14777v1 Announce Type: new Abstract: Large language models are increasingly trained as interactive agents for long-horizon tasks involving multi-turn interaction, tool use, and environment feedback. Outcome-based reinforcement learning (RL) provides a practical optimization paradigm, but
Drawing on more than a decade spent helping build some of the world's most influential AI systems, including research that later informed the development of ChatGPT, Andrew Dai explains why he believes visual AI is one of the next major frontiers in artificial intelligence.
arXiv:2604.07486v3 Announce Type: replace-cross Abstract: Large language models (LLMs) have emerged as a powerful tool for synthetic data generation. A particularly important use case is producing synthetic replicas of private text, which requires carefully balancing privacy and utility. We propose
arXiv:2603.28921v3 Announce Type: replace-cross Abstract: The critical damping condition of the damped harmonic oscillator model of SGD with momentum (Qian, 1999) yields a momentum schedule with no tuned hyperparameters: mu(t) = 1 - 2*sqrt(alpha(t)). Across five seeds on ResNet-18/CIFAR-10 (200-epoc
arXiv:2607.08499v1 Announce Type: new Abstract: We present a Procrustes-conditioned Joint End-to-end Top-K Sparse Autoencoder (SAE) for extracting cross-seed universal features from independently trained BERT models. Cross-seed feature universality is a fundamental challenge in mechanistic interpret
The company is using the cash to open an office in the Bay Area and compete for talent there, "strengthening its position at the heart of the world's leading AI ecosystem."
arXiv:2510.24434v3 Announce Type: replace Abstract: The effectiveness of instruction-tuned Large Language Models (LLMs) is often limited in low-resource linguistic settings due to a lack of high-quality training data. We introduce LuxIT, a novel, monolingual instruction tuning dataset for Luxembourg
arXiv:2607.00248v1 Announce Type: new Abstract: We present Seed2.0, a model series that takes a meaningful step toward solving complex, real-world tasks. Our approach begins with identifying users' genuine needs and constructing a reliable, forward-looking evaluation system by selecting and abstract
arXiv:2605.27729v3 Announce Type: replace-cross Abstract: The 2024-2025 Nobel and Turing awards recognised AI and quantum science simultaneously. Yet no deployed system has brought these streams together for the public. This paper presents QSignAI, a production-deployed platform demonstrating a bidi
arXiv:2605.24903v2 Announce Type: replace-cross Abstract: Machine learning based malware detectors become obsolete over time due to concept drift in benign and malware applications. Recent methods rely on fully labeled data and use hierarchical contrastive loss (HCL) with active learning to improve
arXiv:2606.18833v1 Announce Type: new Abstract: This paper introduces a semi-supervised clustering framework grounded in the statistical duality between grouping principles and anomaly detection. We address the challenge of robust cluster definition in noisy environments -- a task where partitioning
arXiv:2606.19004v1 Announce Type: cross Abstract: Reinforcement learning (RL) post-training of Diffusion Transformers (DiTs) is prohibitively expensive, requiring thousands of high-end GPUs. Existing works explore two directions to reduce cost: seed exploration improves training convergence by selec
Pramaana will focus on highly sensitive verticals like law, drug discovery, and tax preparation — where errors can be costly and reliability is at a premium.
arXiv:2606.12138v1 Announce Type: new Abstract: Sparse autoencoders (SAEs) are widely used to interpret neural network representations, but their utility depends on whether the learned features are reproducible across training runs. We study this question through \emph{feature stability}: for each S
arXiv:2605.28882v2 Announce Type: replace-cross Abstract: With the rapid advancement of large language models, evaluating human-likeness in open-ended conversation has become increasingly important. However, human-likeness is a form of tacit knowledge that humans perceive intuitively, yet the underl
arXiv:2606.10698v1 Announce Type: cross Abstract: In this paper, we use machine learning to discover a new seeding strategy for integration-by-parts reduction of Feynman integrals, which is a frequent bottleneck in state-of-the-art calculations in theoretical particle and gravitational-wave physics.
arXiv:2606.03365v1 Announce Type: new Abstract: Embedding models (KGEMs) constitute the main link prediction approach to complete knowledge graphs. Standard evaluation protocols emphasize rank-based metrics such as MRR or Hits@$K$, but usually overlook the influence of random seeds on result stabili
arXiv:2512.00837v3 Announce Type: replace Abstract: Watermarking acts as a critical safeguard in text generated by Large Language Models (LLMs). By embedding identifiable signals into model outputs, watermarking enables reliable attribution and enhances the security of machine-generated content. Exi
arXiv:2605.27586v1 Announce Type: cross Abstract: Ensuring agent behaviors in distributed open multi-agent systems remains challenging, especially as populations grow and unaligned agents may exist. We show that a single aligned agent can propagate cooperative behaviors to untrained agents purely th
arXiv:2605.23753v1 Announce Type: new Abstract: Knowledge graphs (KGs) offer a rich representation for relational knowledge, but their irregular structure makes retrieval challenging: ego-graph expansion grows rapidly, and dense embedding methods struggle with multi-hop compositional queries. Existi
arXiv:2605.15691v2 Announce Type: replace Abstract: Data selection seeks to identify a compact yet informative subset from large-scale training corpora, balancing sample quality against collection diversity. We formulate this problem as a Weighted Independent Set (WIS) on a similarity graph, where n
NanoClaw was created as a secure alternative to OpenClaw to assist the Cohen brothers with their AI marketing firm that used agents to do much of the work. But instead of running directly on a computer, NanoClaw runs sandboxed in a container.
arXiv:2605.19532v1 Announce Type: cross Abstract: Text-to-image diffusion models can synthesize high-quality images, yet the outcome is notoriously sensitive to the random seed: different initial seeds often yield large variations in image quality and prompt-image alignment. We revisit this "seed ef
arXiv:2605.08313v1 Announce Type: cross Abstract: Large language models (LLMs) rely on deterministic pseudorandom number generators (PRNGs) for autoregressive sampling, creating a critical supply-chain attack surface overlooked by existing defenses. We present SeedHijack, a backdoor attack that mani
arXiv:2604.14655v2 Announce Type: replace Abstract: We present AgentGA, a framework that evolves autonomous code-generation runs by optimizing the agent seed: the task prompt plus optional parent archives that initialize a fresh workspace. The outer loop searches over these reusable starting conditi
arXiv:2605.08319v1 Announce Type: cross Abstract: Mazocarta is a seeded procedural tactical deckbuilder implemented in Rust, compiled to WebAssembly for browser play, and executable natively for simulation. Its primary technical contribution is not the invention of a new deckbuilding genre, but the
arXiv:2605.06300v2 Announce Type: replace Abstract: Deep networks with continuous piecewise affine activations induce polyhedral partitions of the input space, making the number of realized affine regions a natural measure of expressive capacity and a key determinant of how well the model can approx
arXiv:2605.06300v1 Announce Type: new Abstract: Deep networks with continuous piecewise affine activations induce polyhedral partitions of the input space, making the number of realized affine regions a natural measure of expressive capacity and a key determinant of how well the model can approximat
arXiv:2605.04594v1 Announce Type: new Abstract: Many real-world heterogeneous graphs exhibit pronounced heterophily, where connected nodes often have dissimilar labels or play different semantic roles. In such settings, standard heterogeneous graph neural networks that aggregate messages along metap
arXiv:2604.26456v1 Announce Type: cross Abstract: The digitisation of classical Sanskrit literature is impeded by a scarcity of annotated resources, particularly for Named Entity Recognition. While recent methodologies utilise generic Large Language Models (LLMs) for data augmentation, these approac
arXiv:2604.22117v2 Announce Type: replace-cross Abstract: Aligned large language models (LLMs) remain vulnerable to adversarial manipulation, and their reliance on web-scale pretraining creates a subtle but consequential attack surface. We study Stealth Pretraining Seeding (SPS), a threat model in w
arXiv:2603.20092v5 Announce Type: replace Abstract: Diffusion models generate structure by progressively transforming noise into data, yet the mechanisms underlying this transition remain poorly understood. In this work, we show that pattern formation in trained diffusion models can be explained as