Fine-tuning and adaptation

LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.

8,201 stories · RSS feed

arXiv AI

6d ago

MedGemma vs GPT-4: Open-Source and Proprietary Zero-shot Medical Disease Classification from Images

The paper compares the open‑source MedGemma-4b-it model, fine‑tuned with LoRA, to the proprietary GPT‑4 on a six‑disease medical image classification task. MedGemma achieved a mean test accuracy of 80.37%, outperforming GPT‑4’s 69.56%, and showed higher sensitivity for critical conditions such as cancer and pneumonia. Detailed confusion matrices and classification reports illustrate the performance differences across all disease categories.

By Md. Sazzadul Islam Prottasha, Nabil Walid Rafi

llms agents fine-tuning multimodal safety

arXiv AI

6d ago

Explainability-Aware Evaluation of Transfer Learning Models for IoT DDoS Detection Under Resource Constraints

The paper evaluates seven pre‑trained CNN architectures for detecting IoT DDoS attacks under resource constraints, using the CICDDoS2019 dataset and image‑based traffic representation. It combines performance metrics, reliability statistics, latency and training cost, and interpretability methods (Grad‑CAM and SHAP) to assess each model. DenseNet169 and MobileNetV3 emerge as top performers, offering strong reliability, interpretability, and a favorable latency‑accuracy trade‑off for fog‑level deployment.

By Nelly Elsayed

fine-tuning safety

arXiv AI

6d ago

From Geometry to Behavior: How Instruction Exposure Unlocks Latent Rhetorical Directions in LLMs

The paper investigates whether language models possess latent rhetorical abilities, specifically analogy reasoning, before instruction tuning. By extracting an "Analogy Vector" from the residual stream, the authors demonstrate that this vector can steer explanation style across several instruction-tuned models, improving performance metrics. Their findings reveal a continuous gradient of behavioral accessibility tied to the amount of instruction exposure during training, challenging the binary base‑vs‑instruct distinction and suggesting that instruction exposure shapes rhetorical knowledge in activation space.

By Shengjie Xu

llms fine-tuning safety

arXiv AI

6d ago

Think Twice: The Metis-1.6 Technical Report

The report "Think Twice: The Metis-1.6 Technical Report" describes two language models, Praxis (2.94 B parameters) and Logos (10.23 B parameters), built by a single researcher. Both models use a hybrid Mamba‑2 and attention mixture‑of‑experts stack applied twice per token, and were trained on 1.02 T tokens (including pretraining, context extension, and supervised fine‑tuning). While Logos ranks modestly on benchmark tests, it achieves comparable performance to larger models with less training data and fewer active parameters per token, placing it on the Pareto frontier for these metrics. The report also details specific training issues and ablation studies that informed the design of the subsequent Metis‑1.7 architecture.

By Giulianno Vollmer

llms fine-tuning benchmarks

arXiv AI

6d ago

Online Dense Reinforcement Learning with Planning-Grounding Agent for UI Navigation on Live IOS Apps

The paper introduces an online reinforcement learning framework for UI navigation on live iOS apps, separating the agent into a Planning component and a UI Grounding model. It employs an LLM-as-a-Judge to supply dense step-level and terminal rewards, and uses PPO with a novel GiGPPO value estimation to stabilize training. Large-scale infrastructure enables concurrent virtual device training, and experiments on UINavBench, iOSWorld, and AndroidWorld show the approach outperforms supervised fine-tuning and terminal-only RL, achieving significant generalization gains and matching state‑of‑the‑art models on real iOS tasks.

By Peitong Duan, Khashayar Gatmiry, Jeffrey Nichols, Samy Bengio, Emmanuel Abbe

llms agents reinforcement-learning fine-tuning multimodal benchmarks

arXiv AI

6d ago

Decompose, Don't Expand: Capability-Independent AI Systems by Construction

The paper argues that many AI tasks can be split into a deterministic core and a fuzzy residue, and that decomposing tasks rather than expanding models yields a property called parity by construction—where model‑size no longer affects performance on the deterministic sub‑tasks. Across nine models ranging from 494 M to Opus‑class size, the authors show that once the deterministic context is resolved, operation selection and selector resolution scores become identical, while a non‑decomposable task (labelling) remains sensitive to model size. They present a general method for identifying decomposition points, constructing deterministic surfaces and grammars, and ensuring safe residues, and demonstrate the approach in physics, motion retargeting, object‑model editing, and a Web‑CLI tool. whyItMatters":"The study demonstrates that task decomposition can eliminate the need for model scaling or fine‑tuning, offering a systematic design discipline applicable across diverse AI domains."

By Tejaswi Gowda

llms fine-tuning

arXiv AI

6d ago

Encode Once, Answer Many: Internalizing Context via Parametric Flow

Encode Once, Answer Many: Internalizing Context via Parametric Flow proposes CLIK, a context-conditioned parameter generator that transforms a given context into LoRA parameters in a single forward pass, allowing a frozen base model to answer queries without re-reading the context. By internalizing knowledge into model weights, CLIK eliminates per-task optimization and test-time gradient updates, amortizing the cost of reading a document across multiple queries. Experiments show CLIK improves over a no-context base model and outperforms other hypernetwork generators, though it still lags behind models that read the context directly, and it generalizes to multi-turn dialogue without specialized training.

By Xinhao Zhong, Mengxuan Wu, Chonghua Liao, Linxi Xie, Ruicheng Feng, Yanpei Guo, Hao Tan, Jiaxin Hong, Jason Li, Panpan Zhang, Ziheng Qin, Qinglin Lu, Yuzhang Shang, Tongliang Liu, Damian Borth, Haggai Maron, Yongxiang Hua, Zhixiang Wei, Jian Hu, Yunfei Wu, Xing Sun, Xin Li, Haoyu Cao, Zhangyang Wang, Kai Wang

llms nlp fine-tuning

arXiv AI

6d ago

Nemotron 3.5 Super and Lightning: Open, Efficient Mixture-of-Experts Hybrid Mamba-Transformer Models for Agentic AI

Nemotron 3.5 Super and Lightning are open, efficient Mixture‑of‑Experts hybrid Mamba‑Transformer models aimed at reasoning, long‑context understanding, and agentic workloads. Super is a 120 B‑parameter, 12 B‑active multimodal model, while Lightning is a 30 B‑parameter, 3 B‑active text model, both optimized for efficient deployment. The models combine large‑scale distillation, long‑context training, native speculative decoding, and a comprehensive post‑training pipeline that includes supervised fine‑tuning, reinforcement learning, and multi‑teacher on‑policy distillation, enabling Super to function as a multimodal agent capable of reasoning over text, images, video, and interactive tools.

By NVIDIA, :, Aastha Jhunjhunwala, Aayushi Ashokkumar Srivastava, Abhibha Gupta, Abhinav Garg, Abhinav Khattar, Achsah Wildish, Adam Rajfer, Adi Renduchintala, Adil Asif, Adriana Flores Miranda, Aileen Zaman, Aishwarya Chhabra, Akanksha Shukla, Akhiad Bercovich, Alejandra Rico, Aleksa Gordic, Aleksander Ficek, Alex Gronskiy, Alex Steiner, Alexander Bukharin, Alexandre Milesi, Ali Roshan Ghias, Ali Shehper, Ali Taghibakhshi, Alice Gatti, Alisa Liu, Alok Kumar, Alok Tripathy, Amala Sanjay Deshmukh, Aman Miryala, Aman Shanbhag, Ameya Sunil Mahabaleshwarkar, Ameya Velingker, Amir Klein, Amir Samani, Amit Zuker, Amnon Geifman, Anahita Bhiwandiwalla, Ananth Subramaniam, Andre Manoel, Andrea Santilli, Andrew Tao, Andrii Skliar, Anil Thomas, Anish Mahishi, Anna Shors, Anna Warno, Anuj Doshi, Anusha Kamath, Anwith Kiran, Ao Tang, Arham Mehta, Arnab Dhara, Arnav Komaragiri, Arnav Kundu, Arti Jain, Arun Rao, Arun Venkatesan, Arushi Goel, Asha Anoosheh, Ashish Vaswani, Ashwath Aithal, Asif Ahamed, Asma Kuriparambil Thekkumpate, Aswin Visva, Atefeh Sohrabizadeh, Avinash Vem, Ayush Dattagupta, Benedikt Schifferer, Benjamin Chislett, Bernard Nguyen, Besmira Nushi, Bilal Kartal, Bita Darvish Rouhani, Bobby Chen, Boris Ginsburg, Boxin Wang, Brandon Norick, Branislav Kisacanin, Brendan Johnson, Brian Dang, Brian Yu, Bryan Catanzaro, Byung-Kwan Lee, Carlo del Mundo, Chankyu Lee, Chantal Hwang, Charles Wang, Charlie Truong, Chen Cui, Cheng Wang, Cheng-Ping Hsieh, Chenhan Yu, Chenjie Luo, Chintan Patel, Chris Alexiuk, Chris Johnson, Chris Wing, Christian Munley, Coco Li, Collin McCarthy, Cynthia Gao, Dan Su, Dan Zhao, Dane Corneil, Danial Mohseni Taheri, Daniel Afrimi, Daniel Fatade, Daniel Lo, Daniel Machlab, Daniel Serebrenik, Daniele Molinari, Daniil Sorokin, Daria Gitman, Daria Levy, David Mosallanezhad, David Yu, Deepak Narayanan, Dev Churiwala, Devin O'Kelly, Dhruv Nathawani, Di Allan Wu, Dima Rekesh, Dina Yared, Dipendra Misra, Divyanshu Kakwani, Dmitry Belenko, Dominic Manno, Dongyang Fan, Dor Tsur, Duncan Riach, Dustin VanStee, Dylan Lu, Edgar Minasyan, Ehsan Hosseini-Asl, Eileen Long, Elena Lantz, Ellie Evans, Elliott Ning, Elvis Chen, Emanuel Scoullos, Eric Chung, Eric Harper, Eric Pham-Hung, Eric Tramel, Eric Yang, Erik Arakelyan, Evelina Bakhturina, Ewa Dobrowolska, Fadi Saady, Farzan Memarian, Fay Wang, Fei Jia, Felipe Soares, Felipe Vieira Frujeri, Feng Chen, Fengguang Lin, Ferenc Galko, Frankie Siino, Frederic Lafrance, Fuxiao Liu, Gantavya Bhatt, Garvit Kulshreshtha, George Armstrong, Giulio Lovisotto, Gomathy Venkata Krishnan, Gosia Lazuka, Grace Lam, Greg Heinrich, Greg Pauloski, Grzegorz Chlebus, Guilin Liu, Guo Chen, Guoming Zhang, Guyue Huang, Haifeng Qian, Hanrong Ye, Hao Gao, Hao Zhang, Haoqin Tu, Haran Kumar Shiv Kumar, Haribhau Hud, Harris Nover, Harrison Saturley-Hall, Harshil Kotamreddy, Hemil Desai, Henry Estela, Hexin Wang, Himanshu Singh, Hui Wang, Hung-Yueh Chiang, Igor Gitman, Ilia Karmanov, Ilya Loshchilov, Ingo Guehring, Itay Neeman, Ivan Moshkov, Jacky Kwok, Jakub Slowikowski, James Shen, Jane Polak Scowcroft, Jared Casper, Jatin Mitra, Jeff Willette, Jenna Diamond, Jenny Chen, Jesse Oliver, Jessica Medina, Jiacheng Xu, Jialin Song, Jian Hu, Jian Tu, Jian Zhang, Jiantao Jiao, Jiaqi Zeng, Jie-Fang Zhang, Jimmy Zhang, Jin Xu, Jingyu Xin, Jinhang Choi, Joey Conway, Joey Guman, John Kamalu, John Liu, John Roberts, Johnny Greco, Jonah Alben, Jonas Yang, Jonathan Cohen, Jonathan Li, Jonathan Raiman, Joseph Jennings, Juhi Mittal, Julia Gusak, Julien Veron Vialard, June Yang, Junkeun Yi, Jupinder Parmar, Ka Shun Shum, Kaiwen Shi, Kajal Jain, Kanishk Singla, Karan Sapra, Kari Briski, Kateryna Chumachenko, Katherine Huang, Katie Lyons, Keith Wyss, Keshav Santhanam, Keval Morabia, Kevin Shih, Kezhi Kong, Khanh Nguyen, Khushi Bhardwaj, Kiran Praveen, Konstantinos Krommydas, Krishna Puvvada, Krzysztof Pawelec, Kushal Shah, Li Ding, Lily Lee, Linda Liu, Linglin Jing, Luis Vega, Maarten Van Segbroeck, Mahan Fathi, Mahdi Nazemi, Maka Dong, Makesh Narsimhan Sreedhar, Maor Ashkenazi, Marc Cuevas, Marcin Chochowski, Marco Pavone, Markus Kliegl, Marta Stepniewska-Dziubinska, Martina Gonzalez Vilas, Martyna Patelka, Matan Rusanovsky, Matthieu Le, Matty Machczynski, Matvei Novikov, Mauricio Ferrato, Meenakshi Sharma, Mehrzad Samadi, Melissa Corpuz, Melissa Saelzer, Meng Xin, Mengru Wang, Mengxi Wu, Meriem Boubdir, Michael Boone, Michael Callahan, Michael Elad, Michael Lightstone, Michal Bien, Michal Zawalski, Miguel Martinez, Mikail Khona, Mike Chrzanowski, Mike Ranzinger, Mike Wojcikiewicz, Min-Hung Chen, Ming Kang, Mingjie Liu, Mingyuan Ma, Misha Nekorystnov, MJ Mikulski, Mohammad Qazim Bhat, Mohammad Shoeybi, Morgan Purcell, Mostofa Patwary, Nabin Mulepati, Nancy Agarwal, Narimane Hennouni, Nathan Sala, Nave Assaf, Nayeon Lee, Neal Vaidya, Negar Habibi, Netanel Haber, Nick Gupta, Nick Reamaroon, Nickson Quak, Nidhi Bhatia, Nik Spirin, Niket Agarwal, Nikolai Ludwig, Nima Tajbakhsh, Nithin Sunny, Oleksii Hrinchuk, Oleksii Kuchaiev, Olivier Delalleau, Omer Ullman Argov, Pablo Ribalta, Padmavathy Subramanian, Parth Mannan, Pavlo Molchanov, Pawel Morkisz, Peter Jin, Petr Lapukhov, Petro Junior Milan, Philip Monk, Pinky Xu, Piotr Januszewski, Piotr Laszkiewicz, Po-Han Huang, Praateek Mahajan, Pradeep Thalasta, Prakash Gurumurthy, Pranav Prashant Thombre, Prasoon Varshney, Pratyusha Maiti, Preeti Chadha, Pritam Biswas, Pritam Gundecha, Przemek Strzelczyk, Puhui Meng, Pulkit Kumar, Rabeeh Karimi Mahabadi, Rachel Oberman, Rajpreet Thethy, Ramani Akkati, Rameshwar Shivbhakta, Ran Zilberstein, Randy Gelhausen, Rasoul Shafipour, Raviraj Joshi, Ray Macalisang, Rayen Tian, Reka Kovacs, Renjie Pi, Resha Shetty, Ria C, Rima Shahbazyan, Rishabh Garg, Rita Fernandes Neves, Ritika Borkar, Ritu Gala, Riya Talwar, Riyad Islam, Robert Clark, Robert Kirby, Roger Waleffe, Rohan Joshi, Rohan Pillai, Rohit Jena, Rohit Watve, Roi Garnett, Roi Koren, Rongguang Ye, Russell J. Hewett, Ryan Prenger, Ryan Stewart, Ryota Egashira, Sadegh Mahdavi, Sai Nishanth Padala, Salika Dave, Sandhya Rani Narravula, Sandip Bhaskar, Sangkug Lym, Sanjeev Satheesh, Sarah Amirslani, Saran Vikas Murari, Saurabh Mishra, Saurabh Srivastava, Saurav Muralidharan, Sean Narenthiran, Sean Wang, Seokju Cho, Seong Hee Lee, Seonjin Na, Seonmyeong Bak, Seph Mard, Serge Panev, Sergei Kolchenko, Sergio Perez, Seth Henneman, Seth Poulos, Shahar Mor, Shantanu Acharya, Shaokun Zhang, Shaona Ghosh, Sharath Turuvekere Sreenivas, Shaun Kotek, Shaya Gharghabi, Sheng-Chieh Lin, Shengliang Xu, Shi Chen, Shihao Wang, Shilpa Amireddy, Shiqing Fan, Shiyang Chen, Shrimai Prabhumoye, Shriram Venugopal, Shuang Yu, Shubham Gandhi, Shubham Pachori, Shubham Toshniwal, Shuoyang Ding, Shwetha Krishnamurthy, Simeng Sun, Sivakumar Arayandi Thottakara, Somshubra Majumdar, Soumye Singhal, Sridurga Krithivasan, Sriharsha Niverty, Stephen Ge, Sugam Dipak Devare, Sukrit Rao, Sumeet Kumar Barua, Sungsoo Ha, Surya Nistala, Suseella Panguluri, Sweta Priyadarshi, Syeda Nahida Akter, Talor Abramovich, Tanay Varshney, Tandeep Singh Chandehoke, Teo Ene, Terry Kong, Thanh Do, Thinh Le, Tian Zhang, Tijmen Blankevoort, Tim Romanski, Tiyasa Mitra, Tom Balough, Tom Huang, Tomasz Grzegorzek, Tomer Asida, Tomer Bar Natan, Traian Rebedea, Trenton Starkey, Tugrul Konuk, Tuomas Rintamaki, Twinkle Vashishth, Tyler Kniess, Tyler Poon, Udi Karpas, Ushnish De, Utkarsh Vaidya, Vahid Noroozi, Vanshil Atul Shah, Venkat Srinivasan, Venkata Karri, Venmugil Elango, Vibhor Agrawal, Vibhu Jawa, Victor Cui, Victoria Edmonds, Vijay Korthikanti, Vikas Mehta, Vikranth Jeyakumar, Vinay Rao, Vineeth Kalluru Srinivas, Vitaly Kurin, Vitaly Lavrukhin, Wahidur Rahman, Wanli Jiang, Wasi Uddin Ahmad, Wataru Ishihara, Wei Du, Wei Ping, Wei-Ming Chen, Weiheng Chai, Weijia Chen, Wendy Quan, Wenliang Dai, Wenyan Cong, William Zhang, Wojciech Prazuch, Xiaowei Ren, Xin Yu, Xiwen Yu, Yan Wang, Yang Chen, Yang Yu, Yangyi Chen, Yaniv Galron, Yash Jain, Yashaswi Karnati, Ye Yu, Yejin Choi, Yemi Ibrahim, Yev Meyer, Yi Dong, Yi-Fu Wu, Yian Zhang, Yifan Zhang, Ying Lin, Yiyang Zhou, Yoav Miron, Yogendra Pandey, Yonatan Geifman, Yonggan Fu, Yoshi Suhara, Youngeun Kwon, Yu-Cheng Chou, Yu-Chiang Frank Wang, Yuanguo Kuang, Yuekai Zhang, Yugi Guvvala, Yuki Huang, Yunheng Zou, Yunsheng Liu, Zhenming Wang, Zhiding Yu, Zhiqi Li, Zhiyu Cheng, Zhongbo Zhu, Zhuolin Yang, Zichao Yue, Zihan Liu, Zijie Yan, Zirui Liu, Zoe Faul, Zuhair Ahmed

llms agents reinforcement-learning fine-tuning efficiency multimodal benchmarks

arXiv AI

6d ago

Self-training for cross-centre coronary vessel segmentation in X-ray angiography using pre-contrast frame subtraction

The study investigates self‑training for coronary vessel segmentation in X‑ray angiography, using pseudo‑labels from an nnU‑Net model trained on the ARCADE dataset and a contrast map derived from pre‑contrast frame subtraction. Six models were evaluated on ARCADE and two external datasets (XCAD and XACV); first‑round self‑training improved performance over baseline and a fine‑tuned control, with the XCAD model achieving a 2.7‑point Dice score increase. A second self‑training round yielded no further gains, and the benefit of self‑training was found to depend largely on the sensitivity of the initial pseudo‑label generator.

By Danial Moafi, Aida Moafi, Mostafa Aryafar, Ashkan Sami, Maryam Aryafar

computer-vision fine-tuning

arXiv AI

6d ago

Can Event Detectors Leave the Broadcast Camera? Evidence from Tennis

The paper introduces a new benchmark of 345 annotated tennis ball bounces and racket hits across eight video clips featuring diverse viewpoints, including broadcast, fixed elevated, phone, and court-level angles. It evaluates several event detection methods—supervised spotters, zero-shot vision-language models, and a parameter-free arbitration layer called RallyArb—showing that supervised models perform well on broadcast footage but poorly on non-broadcast views, while RallyArb maintains high bounce detection across all viewpoints but struggles with precise hit timing. The dataset, evaluation tools, and frozen predictions are publicly released to support further research.

By David Soeiro-Vuong, Andre-Louis Rochet

llms fine-tuning multimodal benchmarks

arXiv AI

6d ago

Latent Prediction Yields Cross-Subject Alignable Representations in Sensory-Evoked fMRI

The study investigates whether self‑supervised learning can produce useful representations from fMRI data alone. Using a joint embedding predictive architecture, participant‑specific encoders are trained without access to stimulus images or derived representations. The resulting embeddings perform competitively on brain captioning, image reconstruction, and cross‑participant generalization, and can be aligned unsupervised across participants, enabling a decoding head trained on one subject to work on another with minimal loss of performance.

By Serwan Jassim, Victoria Bosch, Daniel Anthes, Elia Bruni, Tim Kietzmann

rag fine-tuning safety

Hugging Face Trending Papers

Oct 29

Elucidating the Design Space of LM Data Attribution

The paper introduces the Controlled Attribution Benchmark (CATT), a synthetic evaluation framework that fine‑tunes language models on entirely fictitious knowledge to provide clear ground truth for data attribution. By systematically varying single dataset properties—such as document redundancy and lexical distractors—CATT reveals that these factors consistently degrade attribution performance. The study also explores two underexamined design choices: using negative log‑odds gradients instead of cross‑entropy gradients, and aggregating only the top token attribution scores, which together improve ground‑truth recall by 35–72 percentage points and enhance counterfactual retraining performance on FTRACE‑TREX by up to 4.9×.

llms fine-tuning benchmarks

Hugging Face Trending Papers

Oct 29

Difficulty Calibration Across Time for Membership Inference in Diffusion Models

The paper introduces techniques to improve membership inference attacks on diffusion models by accounting for image reconstruction difficulty. It proposes Reference-Model Calibration (RMC), which compares a fine‑tuned model’s loss to an earlier checkpoint to isolate newly memorized data, and Temporal Self‑Calibration (TSC), which uses a single model’s loss across diffusion timesteps to adjust for inherent image difficulty. Both methods outperform existing attacks and generalize across various model parameterizations.

diffusion fine-tuning

Hugging Face Trending Papers

Oct 29

Glance: The Generator Is Its Own Reranker

Glance is a retrieval‑augmented generation approach that eliminates the need for separate reranker models by adding a lightweight decision adapter and pointer head to a single 9B backbone. It scores candidate passages directly from a shared prefill, requiring only about 0.1 GiB of extra memory per decision skill. In fine‑tuning on MS MARCO, Glance outperforms the bge‑reranker‑v2‑m3 on SciFact and NFCorpus, and improves answer F1 on HotpotQA by 0.045, while scaling to 200 candidates it surpasses cross‑encoder reranking by 0.058 nDCG@10.

rag fine-tuning

Hugging Face Trending Papers

Oct 29

BRACHIO: Broad Representations Across Centres for Head-and-neck Imaging Oncology (HECKTOR 2026)

The paper reports the submissions of team nucli to the HECKTOR 2026 challenge, which evaluates machine learning methods for head‑and‑neck cancer imaging. The team used self‑supervised pre‑trained encoders, training a 2D DINOv2 encoder on PET scans and combining a DynUNet with a SwinUNETR for segmentation, achieving a mean Dice of 0.5409. For TN staging, they fused geometric features from segmentation masks with PET‑DINOv2‑MIPs deep features via logistic regression, obtaining balanced accuracies of 0.3962 (T‑stage) and 0.6432 (N‑stage). For recurrence‑free survival prognosis, they fine‑tuned the PET‑DINOv2‑MIPs ViT‑S encoder with an MLP head under a CoxPH loss, achieving a Harrell's C‑index of 0.6577 and a weighted challenge score of 0.5802.

computer-vision fine-tuning benchmarks

Hugging Face Trending Papers

Oct 29

M-PFT: Angular Margin for Calibrated Prompt-Tuning of Fine-Tuned Vision-Language Models

M-PFT introduces an angular-margin approach for prompt-tuning of vision‑language models, adding two objectives: reducing maximum cosine similarity among tunable class embeddings to prevent collapse, and aligning each tunable embedding with its zero‑shot counterpart to preserve semantic geometry. This method enlarges the angular margin, thereby correcting base‑to‑novel dual miscalibration and adjusting distorted decision boundaries. Experiments on nine prompt‑tuning methods across fifteen datasets show reduced calibration error on novel classes while maintaining competitive accuracy on base classes with minimal computational cost.

llms rag fine-tuning multimodal

Hugging Face Trending Papers

Oct 29

CASE: Concept-Aware Segmentation from Positive and Negative Visual Exemplars

Few-shot semantic segmentation typically identifies target objects based on positive support examples of a single semantic class. In practice, however, positive cues alone are often underspecified: fo...

computer-vision fine-tuning benchmarks

Hugging Face Trending Papers

Oct 29

UMI-Live for In-The-Wild Bimanual Robotics Data Collection

Universal Manipulation Interface (UMI) devices allow human experts to demonstrate tasks for robot learning without teleoperating physical robots. Using these demonstrations as training data still requ...

robotics fine-tuning data-engineering

Hugging Face Trending Papers

Oct 28

GradSplat: Gradients Inside the Forward Pass for Feed-Forward 3D Gaussian Splatting

GradSplat introduces a feed‑forward 3D Gaussian splatting model that refines its own Gaussian parameters by applying learned gradient steps during the forward pass, without requiring target views. The method corrects Gaussian shape, scale, and rotation through log‑anisotropy adjustments and in‑forward gradient refinement, improving photometric accuracy. On RealEstate10K, DL3DV, and ScanNet++ benchmarks, GradSplat achieves the highest PSNR and SSIM across a range of input view counts, outperforming nine competing methods.

fine-tuning

Simon Willison

Oct 28

GitHub Octoverse 2026

GitHub Octoverse 2026 reports a dramatic rise in activity, with merged pull requests tripling to 220 million per month, commits more than tripling to 7.38 billion per month, and new repositories doubling to 30.3 million per month. The report also provides industry‑specific data and highlights repositories focused on interoperability or reverse engineering. Methodology details include country‑level push adjustments using LLM‑derived ISO codes and NAICS sector classification via a multilingual embedding model.

llms rag agents fine-tuning

Get the daily briefing