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 9, 2026

10 papers found

[object Object], [object Object] 11/6/2026 huggingface

natural language processing

Language model deployment often requires different trade-offs between competing objectives as user preferences change, yet standard post-training methods typically produce a single policy for a fixed objective weighting. We introduce LambdaMix, a new parameter efficient method for learning a prefere...

Keywords: LambdaMix, multi-objective optimization, low-rank adapters, preference conditioning, group-relative policy optimization, parameter-efficient fine-tuning, reinforcement learning from human feedback

[object Object], [object Object], [object Object] 11/6/2026 huggingface

computer vision

LiDAR-based 3D Object Detection (L3OD) is a fundamental 3D perception task, yet its performance is often compromised by domain shifts arising from diverse sensor configurations and environmental conditions. Existing Test-Time Adaptation (TTA) methods primarily leverage self-supervision in the spatia...

Keywords: LiDAR 3D detection, test-time adaptation, frequency domain, domain adaptation, B-Spline, point clouds, autonomous driving

[object Object], [object Object], [object Object], [object Object], [object Object] 11/6/2026 huggingface

multimodal learning

We present PhysioWave-T, a token-efficient wavelet foundation model family for EEG, ECG, and sEMG. Dynamic scale folding recombines J+1 wavelet subbands prior to tokenization, compressing sequence length from (J+1)CS to CS tokens for J levels, C channels, and S temporal patches. Route-specific front...

Keywords: wavelet transform, foundation models, biosignals, EEG, ECG, sEMG, token efficiency, multimodal fusion

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/6/2026 huggingface

ethics ai

LLM agents can exceed their authorization boundaries while pursuing user goals without an adversary. We formalize this phenomenon as authorization drift across data, tool, scope, and time, and introduce the Authorization Drift Benchmark (ADB): 648 samples across seven domains, each pairing a suffici...

Keywords: authorization drift, LLM agents, benchmark, tool use, compliance, legal analysis, data minimisation, AI safety

[object Object], [object Object], [object Object], [object Object], [object Object], [object Object], [object Object] 11/6/2026 huggingface

transformer architectures

Cross-Layer Transcoders (CLTs) decompose the activations of large language models into human-interpretable features and trace how these features interact across layers to form circuits, making them a key tool for mechanistic interpretability. However, training CLTs effectively and efficiently is har...

Keywords: Cross-Layer Transcoders, mechanistic interpretability, sparse coding, TopK, JumpReLU, circuit tracing, LLM interpretability, dynamic sparsity

Peter Belcak, Greg Heinrich, Saurav Muralidharan, Shizhe Diao, Pavlo Molchanov 11/6/2026 arxiv

natural language processing

Large language models reinvent the wheel all the time. They conflate task-solving with the execution of the solutions, which forces them to solve every problem from scratch. We show that once a task has been reasoned through, the application of its solution to a new problem instance can be done very...

Keywords: LLM reasoning, agentic caching, reasoning reuse, CPU inference, explainable AI, test-time compute

Aadya Agrawal, Ho Kei Cheng, Alexander Schwing 11/6/2026 arxiv

generative models

Predicting the future motion of multiple people is inherently stochastic: the same observed history admits many plausible continuations depending on intent, coordination, and social context. Yet the dominant paradigm in multi-person 3D motion prediction remains deterministic, with existing methods p...

Keywords: multi-person motion prediction, flow matching, stochastic forecasting, transformer, B-spline, human motion modeling, conditional generation

Rochak Dhakal, Chen Zhao, Soup Cobb, Xin Qian, Xiaofeng Yang, Weihua Zhou 11/6/2026 arxiv

multimodal learning

Purpose: Surgical operative reports support procedural documentation, surgical training, performance assessment, and workflow review. However, extracting meaningful information often requires extensive manual review and clinical expertise. Automated surgical scene descriptions could reduce this burd...

Keywords: surgical scene captioning, graph neural networks, retrieval-augmented generation, medical AI, computer vision, EndoVis-18

Xingyu Liu, Xiangyang Yin, Tianhua Xia, Haiyu Wang, Sai Qian Zhang 11/6/2026 arxiv

machine learning

Large reasoning models (LRMs) improve task performance by generating longer intermediate reasoning traces, but this substantially increases inference costs and makes low-precision quantization increasingly important. However, aggressively quantized models often perform poorly on reasoning tasks. We ...

Keywords: quantization, large_reasoning_models, LUT_quantization, clustering, activation_outliers, calibration, CUDA_kernel, low_precision

Aaron Sun, Yachan Liu, Ping Yang, Peng Bai, Subhransu Maji 11/6/2026 arxiv

computer vision

Zeolites are an important class of porous crystalline materials with broad applications in gas storage, separations, and catalysis. Although hundreds of thousands of experimentally realized and hypothetical zeolite structures are known, identifying materials optimized for a target application remain...

Keywords: zeolites, self-supervised learning, 3D representation learning, materials discovery, adsorption prediction, benchmark
View Paper
Loading...

Preparing your export...