LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2610.00812v1 Announce Type: cross Abstract: Video generation has rapidly progressed from short, low-quality clips to high-resolution, long-duration sequences with complex spatiotemporal dynamic...
arXiv:2610.02000v1 Announce Type: new Abstract: Adverse conditions such as rain, snow, fog, and dust remain challenging for camera-based perception in autonomous driving. We study multi-class weather...
arXiv:2604.24957v3 Announce Type: replace-cross Abstract: Scaling test-time compute has emerged as a powerful mechanism for enhancing Large Language Model (LLM) performance. However, standard post-tr...
arXiv:2609.31882v2 Announce Type: replace-cross Abstract: Reward-based diffusion fine-tuning faces practical challenges when desirable outcomes are rare or conditioning corrections are costly to esti...
arXiv:2601.22169v2 Announce Type: replace-cross Abstract: Humans are susceptible to undesirable behaviours and privacy leaks under the influence of alcohol. This paper investigates drunk language, i....
arXiv:2604.26766v2 Announce Type: replace-cross Abstract: Accurate and consistent Emergency Severity Index (ESI) assignment remains a persistent challenge in emergency departments, where highly varia...
Selection-Based Structured Reasoning (SSR) is a framework that replaces free-form reasoning with the selection of pre-specified natural‑language reasoning candidates, allowing multimodal agents to choose from a set of reusable high‑level reasoning traces. By scoring these candidates in parallel using a shared context KV cache, SSR eliminates the need for an auxiliary task head and reduces inference cost. Experiments on seven multimodal search benchmarks with 2B and 4B models show that SSR maintains competitive success rates while cutting per‑turn reasoning latency by over 90% and overall inference latency by 28–54%.
Federated fine‑tuning of large language models (LLMs) over mobile radio access networks (RANs) creates recurring, deadline‑sensitive communication workloads that are currently treated as independent device‑originated flows by transport networks. This mismatch hinders efficient resource provisioning, especially for optical circuit switching and all‑photonics transport that require predictable traffic. The paper proposes that future RANs act as learning‑aware traffic shapers, aggregating asynchronous user‑equipment updates at the gNB to produce fewer, bounded‑size transfers that can be scheduled on dynamically provisioned optical links, thereby combining packet‑based access flexibility with programmable transport capacity.
arXiv:2609.36416v2 Announce Type: replace-cross Abstract: Robots operating in real-world environments must often execute complex, multi-step bimanual tasks over long horizons rather than single, isol...
arXiv:2609.40265v1 Announce Type: new Abstract: Real-world time-series applications increasingly require models that can handle time series forecasting, context-conditioned prediction, and language-b...
The paper introduces Quarantined Expert Shutdown (QES), a new backdoor containment strategy for large language models. QES allows backdoor learning to occur during training but routes it into a designated, quarantined expert that can be disabled at deployment. The method achieves significant reductions in attack success rates while largely preserving model utility.
arXiv:2610.01291v1 Announce Type: new Abstract: Recent advances in deep learning for shadow removal have significantly enhanced image quality and realism. However, most approaches rely on real-world...
MoLE introduces a Mixture of Latent Experts framework that encourages distinct latent tokens to extract complementary visual information, rather than sharing visual evidence. By isolating latent visual experts during evidence extraction and aggregating their outputs with dedicated summary experts, MoLE achieves higher performance on visual reasoning benchmarks compared to existing latent reasoning methods. The approach uses a two-stage training pipeline that first forces visual evidence through the latent pathway and then restores direct visual access, without requiring predefined expert roles or intermediate visual targets.
arXiv:2610.01352v1 Announce Type: new Abstract: Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven da...
Hypernetworks have recently shown success in dynamically adapting the parameters of Large Language Models (LLMs) at runtime based on signals such as task descriptions or additional demostrations. Here...
We present Varda-single-1.0, a medium-range data-driven weather prediction system built for the Alpine domain. It provides hourly deterministic regional forecasts on a mesh of 1 km resolution and glob...
Open multimodal reasoning models have benefited from large-scale reasoning supervision, yet reliable post-training remains challenging due to uneven data quality, inefficient supervision construction,...
GUI agents require high-quality interaction trajectories to learn how software environments respond to actions, maintain state, and support multi-step workflows. However, the diversity of available tr...
The paper introduces Rita, a reinforcement learning framework that addresses thinking drift in vision‑language models by enforcing consistency between reasoning and answers. Rita employs two reasoning‑label‑free rewards—thinking and consistency rewards—derived from the conditional probability of reference answers, and uses a difficulty‑aware data filtering strategy to select informative samples for training. Experiments on EgoIntention and RefEgo‑Int benchmarks demonstrate that Rita outperforms both supervised fine‑tuning and vanilla RL‑fine‑tuned approaches.
The paper introduces TSDA-Track, a Template-Search Domain Adaptation framework designed to reduce modality gaps in cross‑modal visual object tracking. Two variants are explored: Pre‑AFA TSDA‑Track uses adversarial alignment before transformer interaction, while Enc‑CFA TSDA‑Track applies contrastive alignment after interaction to strengthen cross‑modal correspondence. Experiments on datasets such as LasHeR, RGBT234, GTOT, and Anti‑UAV‑024 show that both variants outperform state‑of‑the‑art trackers, with Pre‑AFA achieving an SR/PR of 43.2/56.0 on RGBT234 under the modality‑switch protocol.