PlantC2USeg is a deep transfer‑learning framework that uses cross‑scale consistency learning and an information‑restricted decoder to improve plant point cloud segmentation. It achieves state‑of‑the‑art performance on Soybean3D and ShapeNet Part, and demonstrates strong few‑shot generalization across species and sensing conditions. The method reduces the need for large annotated datasets and lowers adaptation overhead for new plant species.
By Yu Tian, Xintong Jiang, Jan Franklin Adamowski, Shiv O. Prasher, Shangpeng Sun
IDEA is a training‑free, input‑dependent steering method for large language models that matches activations to cluster‑specific directions aligned with a target concept. It clusters positive and negative activation supports per attention head, solves an optimal‑matching problem to create a pool of cluster‑conditional directions, and selects the best match for each input at inference time. This approach preserves the input’s original representation while improving the truth × info rate on TruthfulQA by an average of 9.9% (up to 23.5%) over input‑independent baselines.
By Zheng Wang, Muchen Li, Renjie Liao, Yan Leng
Freeze, Diffuse, Decode (FDD) is a diffusion-based framework that adapts pre‑trained transformer embeddings to downstream tasks while preserving their geometric structure. By propagating supervised signals along the intrinsic manifold of frozen embeddings, FDD produces low‑dimensional, predictive, and interpretable representations. In antimicrobial peptide design, these representations support property prediction, retrieval, and latent‑space interpolation.
By Pankhil Gawade, Adam Izdebski, Myriam Lizotte, Kevin R. Moon, Jake S. Rhodes, Guy Wolf, Ewa Szczurek
VideoPulse is a neonatal dataset and end‑to‑end pipeline that estimates heart rate and peripheral capillary oxygen saturation (SpO2) from facial video without contact. The dataset contains 157 recordings from 52 neonates, and the pipeline uses face alignment, artifact‑aware supervision, and 3D CNN backbones to produce predictions every 2 seconds. On the NBHR dataset the model achieves a heart‑rate MAE of 2.97 bpm and SpO2 MAE of 1.69 %.
"whyItMatters":"The results show that short, unaligned neonatal video segments can accurately estimate vital signs, offering a low‑cost, non‑invasive monitoring option for neonatal intensive care."
By Deependra Dewagiri, Kamesh Anuradha, Pabadhi Liyanage, Helitha Kulatunga, Pamuditha Somarathne, Udaya S. K. P. Miriya Thanthrige, Nishani Lucas, Anusha Withana, Joshua P. Kulasingham
The 2026 PNPL Competition builds on the 2025 PNPL effort by expanding the LibriBrain dataset to 32 new subjects and more within‑subject data, creating LibriBrain100. It introduces two tracks: a Deep track for high‑performance within‑subject word classification and a Broad track that tests cross‑subject generalisation with progressively less subject‑specific fine‑tuning data, down to about 10 minutes. The goal is to move toward a practical, non‑invasive brain‑computer interface that can restore communication for people with profound paralysis.
The paper investigates whether the rank of matrix-valued latent representations in continuous chain‑of‑thought models influences task accuracy. Experiments on ProsQA and GSM8K‑Aug show that truncating the latent matrix to low rank has negligible effect (within 0.6 pp), and this flatness persists across various readout designs and even in a vanilla GPT‑2 baseline. The results suggest that rank is not a useful structural signal for these models’ reasoning paths.
SafeEvolve is an experience-driven framework that co‑evolves a harness and policy to improve safety alignment for LLM‑based agents. It uses on‑policy trajectory safety evidence to update safety prompts and hierarchical skills, producing auditable harness artifacts. The policy is trained via a two‑stage SFT‑RL pipeline that bootstraps with the evolved harness and then refines behavior through verifier‑decomposed rewards, yielding a better safety‑utility tradeoff on benchmarks such as AgentDojo.
Low-rank adaptation (LoRA) is the standard way to fine-tune large models, yet when its two factors are trained independently, the update ignores the geometry of the low-rank weight change it induces. We introduce LoRA-TSD, an optimizer that treats every LoRA step as a tangent vector of the fixed-rank matrix manifold and takes the spectral-norm steepest-descent step of Muon inside that tangent space, mapping the result back to the factors through a retraction native to the LoRA parametrization.
The paper introduces DKL, a method that decouples knowledge learning from instruction tuning in language models. Instead of fine‑tuning the instruction‑tuned model directly, DKL first extends pre‑training on a base model to embed new knowledge, then merges these weights into the instruction‑tuned model, preserving its instruction‑following abilities. Experiments show DKL raises RAG accuracy from 54.17 % to 79.26 % on retrieval failures, outperforming prior methods while using far less training data.
The paper introduces the first publicly available dataset for predicting left ventricular ejection fraction (EF) from parasternal long-axis (PLAX) echocardiography, comprising over 25,000 labeled videos generated through a novel data‑generation strategy that correlates clinical notes with echocardiographic videos. Using this dataset, the authors train a reproducible PLAX‑EF model that achieves a mean absolute error (MAE) of 6.86%, comparable to the clinical standard of apical four‑chamber (A4C) methods. They further show that combining PLAX and A4C predictions via simple late fusion reduces MAE to 6.37%, highlighting the benefit of multi‑view integration, and they release the dataset, models, and demos for community use.
CoMerge introduces a conflict‑driven preference optimization framework for merging multi‑task large language models, reframing merging as a preference problem that uses self‑supervised hard negative samples derived from naive merging defects. By optimizing lightweight, tensor‑wise merging coefficients, the method mitigates parameter‑space conflicts while preserving task‑specific capabilities. Experiments show CoMerge achieves an average normalized performance of 0.9968 on MergeBench and improves conflict‑sensitive tasks on Llama‑3.1‑8B‑Instruct, outperforming both data‑free and data‑driven baselines while optimizing only 1,445 scalar coefficients.
The paper demonstrates a lightweight method to adapt general-purpose vision‑language models (VLMs) for multispectral and synthetic aperture radar (SAR) image understanding. By rendering each observation as five optical views and one SAR view, naming them in the prompt, and applying LoRA to the language network and selected visual transformer blocks, the authors enable VLMs to process band composites, spectral indices, and radar backscatter without retraining a new foundation model. On a balanced six‑class land‑cover benchmark from BigEarthNet‑v2, the adapted Qwen3‑VL achieves a micro F1 score of 0.8275, and the same protocol improves four other VLMs and transfers to flood verification and captioning tasks.
IDEA: training-free Input-Dependent stEEring via Activation cluster matching (IDEEA) is a method that steers large language models by injecting bias into selected activations at inference time, without requiring weight updates. Unlike existing training-free steering approaches that use a single, input-independent direction, IDEEA clusters positive and negative activation supports per attention head and solves an optimal-matching problem to create a set of cluster-conditional directions. At inference, IDEEA selects the direction that best matches the input’s activation, aligning the model toward a target concept while preserving the input’s original representation, and achieves a 9.9% average improvement in truth × info rate on TruthfulQA compared to the best input-independent baseline.
The study evaluates large language models (LLMs) as rerankers in conversational movie recommendation, comparing proprietary, open-weight, and fine-tuned LLMs against collaborative-filtering and sequential baselines on the ReDial benchmark. Results show that the best proprietary LLM achieves an NDCG@10 of 0.1497 with a shared semantic candidate pool, outperforming non-LLM baselines, while open-weight LLMs do not surpass a tuned shallow autoencoder under the same protocol. The analysis also highlights that reranker performance is highly sensitive to candidate generation, pool size, scoring policy, and decoding temperature, suggesting these factors should be reported as standard evaluation fields.
By Ante Kapetanovic, Tomislav Duricic, Andro Mercep, Emanuel Lacic
The paper introduces MiNER, a fine‑tuned biomedical NLP system that uses BioBERT to extract malaria‑related named entities from scientific literature. It builds a large, annotated corpus of malaria articles, preprocesses the text, and applies supervised learning to improve extraction performance. Experiments show that MiNER outperforms other encoding and machine‑learning methods in precision, recall, and accuracy, and the authors release the human‑labeled dataset for further research.
By V. S. Anoop, Devika N
arXiv:2609.01294v1 Announce Type: new
Abstract: Deep-research agents answer complex questions by interacting with search and browsing tools, yet they often search along a single evolving trajectory....
By Ruochen Zhou, Zhengyu Chen, Luan Zhang, Siyang Gao, Yee Whye Teh, Shiqi Chen
The paper introduces DroneCATS-Agent, a modular framework that places a multimodal large language model (MLLM) at the core of a drone’s control loop, allowing the model to decide actions solely from prompts. It presents the DroneCATS benchmark, evaluating MLLMs on four tasks—approaching, tracking, searching, and multi‑drone commanding—without fine‑tuning or function‑calling. Results show that while small open models can navigate reliably, they often fail by mismanaging protocol termination, highlighting a gap between perception and action planning in current MLLMs.
By Jaewoo Park, Minyoung Lee, Sukmin Seo, Moonbin Yim, Hyunwook Yoon, Dohoon Ryu, Daehee Kim, Myungseo Song, Jihyuk Byun, Seunggyu Chang, Taeho Kil, Jiseob Kim, Bado Lee, Geewook Kim
The paper introduces Iterative MBR Distillation for Error Span Detection (ESD) in machine translation, a self‑evolution framework that replaces human annotations with pseudo‑labels generated by a large language model. By iteratively applying Minimum Bayes Risk decoding, the method produces high‑quality error spans without costly human effort. Experiments on WMT Metrics Shared Task datasets show that models trained solely on these pseudo‑labels outperform both unadapted baselines and supervised models trained on human data at system and span levels, while keeping sentence‑level performance competitive.
By Boxuan Lyu, Haiyue Song, Zhi Qu
arXiv:2609.00228v1 Announce Type: new
Abstract: Scientific domain entity linking (EL) differs from general domain EL because mentions and entity names often lack lexical overlap. Another challenge is...
By Md Rasel Khondokar, Qiao Qiao, Farjana Sultana Samia, Nhat Le, Yuepei Li, Qi Li