Paper Archive

Browse and export your curated research paper collection

403
Archived Days
3953
Total Papers
7.3
Avg Score
12
Categories

Export Archive Data

Download your archived papers in various formats

JSON: Complete data with analysis | CSV: Tabular data for analysis | Markdown: Human-readable reports | BibTeX: Academic citations
Browse by Date

Papers for November 3, 2026

10 papers found

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/2/2026 huggingface

transformer architectures

Computer programmers chain together the same reusable computational primitives, for example, conditional statements or loops, but in different orders to implement different algorithms. In contrast, existing language model architectures always execute their layers in the same order. We introduce Libr...

Keywords: transformer architecture, dynamic computation, mixture of experts, adaptive inference, routing mechanisms, parameter efficiency

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/2/2026 huggingface

multimodal learning

Multimodal large language models (MLLMs) can generate detailed video captions, yet they may overemphasize minor details while overlooking essential context and key events. We argue that not all visual evidence deserves equal attention, as the importance of visual information depends on the content o...

Keywords: video captioning, multimodal LLM, active perception, agentic framework, reinforcement learning, GRPO, observation planning

[object Object], [object Object], [object Object] 11/2/2026 huggingface

transformer architectures

Attention remains a substantial computational cost in Transformer training, particularly at long context lengths. NVIDIA Blackwell GPUs provide high-throughput low-precision matrix multiplication, but exploiting it in attention requires addressing quantization overhead, causal information leakage th...

Keywords: attention, quantization, MXFP8, NVFP4, Blackwell GPU, Transformer training, causal attention, low-precision training

[object Object], [object Object], [object Object] 11/2/2026 huggingface

generative models

Text-to-CAD generation aims to make CAD modeling more accessible by generating executable CAD programs from natural-language descriptions. However, practical CAD workflows require more than executable geometry: generated programs should also expose reusable structure that supports later modification...

Keywords: text-to-CAD, intent-oriented generation, semantic-parametric supervision, CadQuery, zero-shot editing, dataset construction

Ziqi Pang, Yu-Xiong Wang 11/2/2026 arxiv

reinforcement learning

Reinforcement learning with verifiable rewards (RLVR) can enable generalizable improvement for large language model (LLM) reasoning. This paper studies how to incentivize such generalization via reasoning strategies. We study this question with a controllable equation-solving framework: finding mult...

Keywords: RLVR, LLM reasoning, out-of-distribution generalization, reasoning strategies, reinforcement learning, verifiable rewards

Paulius Skaisgiris, Thomas Pammer, Veronika Semmelrock, Mykyta Ielanskyi, Maximilian Heisinger, Erich Kobler 11/2/2026 arxiv

natural language processing

Chain-of-Thought (CoT) generation has substantially improved the performance of Large Language Models (LLMs) on complex reasoning tasks, including code generation, data analysis, and exam-style question answering. Despite these advances, purely neural LLMs continue to struggle with elementary logica...

Keywords: neuro-symbolic, LLM, exact cover, Zebra puzzles, reasoning, semantic parsing

Marius Memmel, Shawn Yin, Urvi Rutia, Angad Wadhwa, Eldon Li, Gavin Angeloff, Ankit Goyal, Jesse Zhang, Dieter Fox, Fabio Ramos, Anqi Li, Abhishek Gupta 11/2/2026 arxiv

robotics

Vision-Language Models (VLMs) hold promise for zero-shot video task-progress estimation in robot learning, yet existing frameworks frequently suffer from confirmation bias, hallucinating progress in failed executions due to implicit success assumptions or relative temporal ranking designs. Naive pro...

Keywords: Vision-Language Models, Robotics, Reward Models, Zero-Shot Learning, Prompt Engineering, Reinforcement Learning

Yujiao Shen, Jiahe Song, Haitian Li, Jingkang Yang, Ziwei Liu 11/2/2026 arxiv

computer vision

Learning from human data offers a scalable path toward embodied intelligence, yet it requires models to accurately understand fine-grained human actions from egocentric observations. However, existing benchmarks remain limited in action atomicity, temporal precision, and hand-action association. We ...

Keywords: egocentric vision, dense action captioning, embodied intelligence, hand-action association, benchmark, reinforcement learning, video understanding

Tomas Duncun, Jonah Ellison, Mateo Ruiz, Hanae Fujita, Ingrid Solberg 11/2/2026 arxiv

reinforcement learning

Group-based reinforcement learning with verifiable rewards (RLVR) learns only from prompts whose sampled completions disagree: all-pass and all-fail groups produce zero relative advantage and burn generation budget without moving the policy. Adaptive schedulers try to steer rollouts toward informati...

Keywords: RLVR, reinforcement learning, online scheduling, ability-difficulty estimation, Pólya-Gamma augmentation, Woodbury identity, reasoning benchmarks

[object Object] 11/2/2026 huggingface

transformer architectures

A model pretrained to predict a customer's next event can estimate the probability of future events without training on their labels and provide a reusable representation for supervised downstream banking tasks. We pretrain EventGPT, a hierarchical causal transformer, by next-token maximum likelihoo...

Keywords: EventGPT, hierarchical transformer, next-event prediction, banking, zero-shot learning, MBD-mini, causal transformer, multimodal sequences
Loading...

Preparing your export...