LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2609.40108v1 Announce Type: new Abstract: Opioid overdose remains a major clinical and public health burden, highlighting the need for scalable approaches to identify patients at high risk. Her...
Cryo-Bench is a new benchmark that evaluates foundation models for cryosphere mapping, comprising six semantic‑segmentation datasets across five cryospheric components (supraglacial debris, glacial lakes, sea ice, calving fronts, and Antarctic ice‑shelf extent). The benchmark includes multispectral, RGB, and SAR observations from under‑represented regions and tests thirteen geo‑foundation models alongside U‑Net and Vision Transformer baselines. Results show that with frozen encoders U‑Net slightly outperforms TerraMind, but the difference is not statistically significant; fine‑tuning with learning‑rate optimization can dramatically improve performance for some models, while in few‑shot scenarios several foundation models retain over 90 % of their full‑label accuracy.
arXiv:2609.39578v1 Announce Type: new Abstract: Agent harnesses often improve language models with human-designed workflows, but as models grow more capable, unreliable guidance can increasingly cons...
GroundAnything is a 4‑B parameter grounding foundation model that combines autoregressive and diffusion approaches to achieve fast parallel decoding while maintaining precise visual grounding. By treating grounding as visual evidence extraction and using blockwise denoising, it allows spatial hypotheses to be generated in parallel and refined iteratively. The model outperforms existing state‑of‑the‑art methods on 30 grounding benchmarks, achieving 72.42% accuracy with its autoregressive variant and 61.75% with entropy‑guided decoding, while also offering significant speedups through optional self‑speculative decoding.
OmniReasoning introduces a new benchmark, OmniReasoningBench, that requires both audio and visual evidence for answering 1,150 multiple-choice and open-ended questions across two tasks. The authors also develop OmniQA, a data engine that automatically generates evidence‑grounded QA pairs with time‑stamped clue chains, producing training datasets OmniReasoning‑SFT‑112K and OmniReasoning‑RL‑19K. Finally, they propose Modality‑Factored Self‑Distillation (MFSD), an on‑policy self‑distillation method that assigns token‑level credit by evaluating responses under modality‑specific clue contexts, enabling the OmniReasoning‑30B‑A3B model to achieve significant performance gains on both the new benchmark and existing video benchmarks.
arXiv:2609.40356v1 Announce Type: cross Abstract: Recent video generation is increasingly realistic and controllable, yet video editing remains less developed, particularly for precise local edits th...
In this paper, we study how to achieve one-step action generation in Robotic Foundation Models (RFMs), aiming to overcome the high inference latency of multi-step flow matching. MeanFlow provides a pr...
Pre-training interventions are critical to alignment research, since beliefs formed during pre-training shape how a model generalizes from later training. One recently popular technique for such inter...
Online training enables computer-use agents (CUAs) to improve through interaction with executable environments. However, existing methods primarily rely on sparse outcome rewards, which provide no sup...
Converting free-text radiology reports into structured labels supports cohort building, quality assurance, and monitoring of clinical imaging models, but the strongest label extractors are hosted prop...
Sparse triangular solve (SpTRSV) is a fundamental kernel in numerous scientific and engineering applications. However, the data dependencies inherent in sparse triangular matrices significantly limit...
Purpose: This study examines whether domain-specific public mood is associated with stock-market dynamics and whether these relationships vary across communication domains and market conditions. It di...
Source-Free Universal Domain Adaptation (SF-UniDA) extends Universal Domain Adaptation by removing access to source data at adaptation time while still handling label-set mismatches between domains. D...
Recent diffusion-based pipelines have achieved promising progress in image-to-3D synthesis. However, generating high-fidelity details remains challenging, especially when the input image contains rich...
This paper demonstrate that whether masking-based token pruning helps or hurts worst-group robustness can be predicted before deployment, without labels or fine-tuning. A systematic study of semantic...
Deploying vision-and-language navigation (VLN) agents in unseen environments remains challenging because unfamiliar layouts and visual conditions can cause execution to go off track. Rather than relyi...
Recent advances have enabled unified omni-modal models in understanding audio, vision, and language. However, existing benchmarks, training data, and learning methods largely treat the modalities inde...
Neural operators increasingly benefit from pretraining on numerical simulations, yet adapting them for real-world prediction remains challenging. We introduce the Retain-and-Repair Neural Operator (R$...
A deep classifier is defined not only by the decision it produces, but also by the sequence of transformations through which that decision is formed. Treating this evolution as a dynamical system acro...
This paper studies \textbf{thinking--answer consistency} in vision-language models. We focus on Visual Intention Grounding, where a model infers a target object based on a human intention query and pr...