Explore tools, prompts, skills, news and resources related to ACT 第34页.
Prompt works related to ACT 第34页
Latest articles, prompts, use cases and editorial content about ACT 第34页
This paper introduces Structure from Collision (SfC), a method to recover hidden interior cavities of objects from multiview collision observations. The authors reformulate SfC as hypothesis-space reasoning, using gradie...
This paper compares three retrieval designs for conversational agents: skill-based retrieval, non-persistent subagent, and a persistent retrieval subagent that maintains history across turns. The persistent approach redu...
DISCERN is a new method for incremental class unlearning that removes classes from a model sequentially without access to the retain set. It fits per-class parametric distributions to synthetic embeddings, selecting the...
A new arXiv paper decomposes the effects of quantization and pruning on language models, separating direct damage from network compensation. The authors find that for comparable damage, smaller models restore most of the...
This paper studies active in-context learning for tabular foundation models (TFMs), where labels are acquired iteratively to build the context. The authors propose and evaluate target-aware and information-gain-based acq...
Researchers present InnerLogic-Surg, an open family of surgical vision encoders (21M–300M parameters) obtained by continually pretraining a transformer on millions of surgical images from nearly 3,000 hours of video span...
Researchers propose NEDNet, a neural network that decomposes outcome responses into baseline, treatment, and exposure pathways for causal effect estimation under network interference. It uses path-specific neighborhood c...
CORE is a new training-free harness for deep research agents that balances long-passage retrieval with short evidence snippets. It uses a dense retriever for coarse search and a late-interaction reranker to extract only...
Researchers tested whether frontier LLMs (GPT-6 Astra and others) can audit small clinical prediction networks by inspecting their weights or using a calculation tool. Without tools, Astra succeeded on 353-weight network...
This paper presents a theoretical framework linking masked diffusion models for text generation to statistical physics of driven many-particle systems. It shows that the error in parallel decoding corresponds to entropy...
STAG-Net is a new lightweight head pose estimation method that uses structure-aware attention over landmark groups, achieving state-of-the-art accuracy among landmark-based approaches on standard benchmarks. It requires...
Researchers find that frozen dense embedding models poorly capture time, place, person, and event axes in personal-memory retrieval, with axis changes barely shifting embeddings. They propose Axis-LoRA, a per-axis adapte...
A new arXiv paper identifies a mechanism called the Intrusion Pathway that explains why language models lose accuracy when prompts contain irrelevant, off-topic context. The authors localize the problem to a sparse set o...
RIVER is a multi-agent framework that coordinates LLMs, biochemical tools, and knowledge resources to perform bidirectional enzyme–reaction retrieval. It assembles multi-level evidence and uses validation modules to rera...
This paper investigates how the number of unique activations affects sparse autoencoder (SAE) training when the total training budget is fixed. It finds that quality improves rapidly with buffer size but then plateaus, w...
RELOAD is a method that retrofits loops into pretrained decision models, allowing them to spend variable test-time compute in latent space without adding parameters. When trained with the model, these loops improve accur...
This paper investigates whether LLM token probabilities can serve as confidence estimates in human behavior simulation, using a Next Like Prediction task on Luxembourgish news platform data. The authors find that open-we...
This paper introduces O²PD, a new method for on-policy distillation in language models. It addresses two key questions: which tokens to align and how to align them. The method applies distillation only to the first 20% o...
Researchers propose a training-time approach for human-like navigation in multi-agent scenes, using world models as preference oracles to distill foresight into a fast policy. Two task-aligned world models score candidat...