hackernews: 正常(20 条) github: 正常(20 条) arxiv: 正常(20 条) arxiv-rss: 正常(20 条)
  1. arxiv-rss · · Snehalkumar `Neil' S. Gaikwad, Dhruv Dixit, Bryen Alvarez, Pratik Patekar, Anika Sharma, Akshara Kolipaka, Paritosh Pandey

    arXiv:2611.17564v1 Announce Type: new Abstract: Governments are writing rules for artificial intelligence that decide what counts as an automated decision or a harm, often before the people they affect have a chance to question them. We introduce AI-Voyager, a public-interest system for human-AI civic reasoning, in which people and AI work together to understand, contest and shape the rules that govern AI. A resident can find their city's rules on AI in hiring or upload their country's AI strate…

  2. arxiv-rss · · Samuel Chen, Jiaru Bai, Austin Henry Cheng, Varinia Bernales, Al\'an Aspuru-Guzik

    arXiv:2611.17539v1 Announce Type: new Abstract: Autonomous crystal-structure determination from powder X-ray diffraction (pXRD) remains a key bottleneck for self-driving materials laboratories. We formulate the task of pXRD structure determination as a verifiable agentic search problem: candidate structures can be assessed during inference through forward-simulated profile agreement and during evaluation through structural matching to a known reference. To benchmark progress, we introduce pXRD-B…

  3. arxiv-rss · · Kate M. O'Neill, Ian Whitehouse, Adam N. McCaughan, Ryan O'Loughlin, Sonia Buckley, Wolfgang Losert

    arXiv:2611.17532v1 Announce Type: new Abstract: Conductors are critical for the performance of an orchestra even though they do not emit sound. Basic research and clinical studies in the last decade are revealing that astrocytes may be the "conductors" of the "orchestra" that is the brain network: astrocytes make up approximately $50\%$ of all brain cells but do not emit electrical signals. Nevertheless, they may play critical roles in important cognitive brain functions, specifically learning,…

  4. arxiv-rss · · Ali Mohammadi Ruzbahani, Rezvan Abouzadeh

    arXiv:2611.17524v1 Announce Type: new Abstract: A small labelled dataset is memorized long before the training budget runs out, and the one-hot labels that remain to be fitted then mostly sharpen confidence. Model annealing spends the rest of the budget on review and consolidation, relearning from the network's own knowledge. Training is divided into episodes whose learning rate is raised again and cooled, every cooled state joins a memory of past selves, and each new episode learns from the lab…

  5. arxiv-rss · · Harrison C. Margolin

    arXiv:2611.17515v1 Announce Type: new Abstract: Can sustained gain-loss (valence) framing sway an LLM agent toward market manipulation? We place Gemma 3 12B into the seat of a defendant in the London silver-fixing litigation, in a market simulation built from real case transcripts. Across 260 simulations, the agent is asked to collude on the price of silver by a counterparty. We draw from behavioral economics to vary the counterparty's requests across four categorical frames: gain, loss, blame a…

  6. arxiv-rss · · Yavuz Yetim, Bor-Yiing Su, Zhe Wang, Arthur Liu, Pranav Sharma, Ying Wang, Randy Shuai, Luke Pfister, Ruichao Xiao, Bill Zhao, Zihao Liu, Liyuan Li, Jiangyuan Li, Gaoxiang Liu, Nathan Yan, Geonhwa Jeong, Jatin Chhugani, Elias Ellison, Uladzimir Pashkevich

    arXiv:2611.17501v1 Announce Type: new Abstract: Recommendation and Ranking (R&R) models, particularly in digital advertising, require massive inference throughput but exhibit extreme sensitivity to precision loss. Unlike Large Language Models (LLMs) that frequently tolerate quantization-induced accuracy drops of 1% or more, production-grade R&R models enforce a stringent launch bar: model quality must remain within a 0.01% Normalized Entropy (NE) margin relative to the baseline, which commonly u…

  7. arxiv-rss · · Nathan Sheffield, Alek Westover, Lukas Finnveden, Alexa Pan, Julian Stastny, Ryan Greenblatt

    arXiv:2611.17495v1 Announce Type: new Abstract: Chain-of-thought (CoT) is currently a valuable tool for overseeing AI models, but some architectural shifts could significantly reduce CoT monitorability. We operationalize a measure that serves as a proxy for the amount of unverbalized serial cognition a model can perform, as a specific instantiation of the notion of opaque serial depth: roughly, the length of the longest path through a model's computation that does not pass through an interpretab…

  8. arxiv-rss · · Animesh Agarwal, Meysam Ghaffari, Nina Fatehi, Carlos Morato

    arXiv:2611.17341v1 Announce Type: new Abstract: Medication prediction from electronic health records is a fixed vocabulary structured prediction problem, yet recent clinical RAG systems often treat it like open ended case based reasoning: retrieve similar patient admissions and ask an LLM to infer a medication set. This retrieval object is indirect the model receives retrieved patient records while the target is a discrete set of medication class labels. We propose a more task aligned retrieval…

  9. arxiv-rss · · Inish Melroy D Souza, Tom Jackson, Vitor Castro, Rebecca Higginson, Andrea Soltoggio

    arXiv:2611.17340v1 Announce Type: new Abstract: Large language models are expensive to update through full retraining. Parameter-efficient fine-tuning reduces the cost of adaptation, but repeated adaptation creates a growing pool of task-specific LoRA adapters. This pool complicates adapter selection during inference. Existing routing and encoder-based methods often require retraining when new adapters are added, which limits their use in dynamic settings. This paper treats adapter routing as a…

  10. arxiv-rss · · Shubhra Mittal, Gaurav Naresh Mittal

    arXiv:2611.17339v1 Announce Type: new Abstract: Hallucination detection for large language models is dominated by methods evaluated on 7B-70B research models with abundant sampling budgets and exact-match or ROUGE correctness labels. The small models practitioners actually ship on-device, Phi-3-mini, Llama-3.2-3B-Instruct, Qwen2.5-3B-Instruct, and Gemma-2-2B-Instruct, typically at 4-bit precision, sit outside this evidence base. We present a reproducible one-GPU audit of four detectors spanning…

  11. arxiv-rss · · Samarth Vinayaka

    arXiv:2611.17338v1 Announce Type: new Abstract: LLM memory systems often delete facts classified as stale. We show that this hard-filtering step can reduce downstream accuracy when resolver errors delete query-critical facts. Across three models, a controlled sensitivity intervention moves hard-drop from gains of +0.186 to +0.230 at perfect resolution to losses of -0.176 to -0.181 at the lowest tested reliability. Paired targeted interventions show that false-drop causes significantly greater de…

  12. hackernews · · speckx
  13. #33 n8n-io/n8n 20.6
    github · · n8n-io

    Fair-code workflow automation platform with native AI capabilities. Combine visual building with custom code, self-host or cloud, 400+ integrations.

  14. github · · firecrawl

    Supercharge your AI agents with data from the web and beyond. Building the library for superintelligence. 🔥

  15. arxiv · · Akshay Vyas

    We present Neural Dual Bounds, a calibration-free framework that produces deterministic upper bounds for MAP inference in probabilistic graphical models using a single neural-network forward pass. The framework trains a network to output the edge messages of a mini-bucket style upper bound on a given join-graph decomposition in a self-supervised manner by directly minimizing a smooth dual objective. The output of this network can be used at test time to warm-start a standard JGLP optimizer. Acro…

  16. arxiv · · Youngseok Yoon

    Bayesian optimization (BO) enables sample-efficient search for expensive black-box problems, but its performance depends strongly on surrogate-acquisition configurations whose suitability varies across problems and optimization states. We take a significant step toward LLM-driven strategic management of BO with STaSBO, a task-agnostic meta-controller that plans search behavior and jointly selects surrogate-acquisition configurations, while numerical BO retains responsibility for probabilistic mo…

  17. arxiv · · Pengyu Chen

    Text-to-video (T2V) generation models can produce systematically unfair demographic outcomes when prompts leave protected attributes unspecified. For example, prompts describing nurses without specifying gender may disproportionately generate videos depicting female nurses. Mitigating unfairness in T2V generation is particularly challenging: training-based methods that modify model internals require architecture-specific access and risk disrupting temporal consistency, while sampling-based metho…

  18. arxiv · · Zane Fu

    On-policy distillation (OPD) is emerging as an important paradigm for the post training of large language models, improving student models by leveraging supervision generated online by teacher models. However, whether this process also transfers latent security risks from teacher models to student models remains insufficiently studied. In this work, we reveal a new security risk in which an attacker first implants a conditional backdoor into the teacher model through supervised fine tuning (SFT)…

  19. arxiv · · Nikhil Kumar Jha

    LoCoMo is a widely reported benchmark for long-term conversational memory, but published scores mix memory quality with choices of answer prompt, judge and baseline layout that are rarely reported together. We measure how much these choices move a score, and evaluate Becos, a team memory system for coding agents, as a black box under all of them: ten conversations (1,540 questions), two answer models (gpt-4o-mini, gpt-4.1-mini), two answer prompts and three LLM judges, against a whole-conversati…

  20. hackernews · · kristjansson