LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2609.00491v1 Announce Type: new Abstract: Communicating across cultures is inherently challenging, especially through culturally dense and ambiguous formats like memes. While people expect larg...
The paper introduces a new consistency criterion for auditing decision systems that combines ensemble margin with local prediction variability to address predictive multiplicity, or the Rashomon effect. It shows that finite ensembles converge to the expected model’s consistency score as ensemble size and sample count grow, and demonstrates that ensembling models from the Rashomon set reduces unchecked incorrect predictions while keeping diversions moderate. Experiments on transformer and fine‑tuned language models for NLP and tabular classification confirm the method’s effectiveness and stronger alignment with existing multiplicity metrics.
ViTAMINS is a method that incorporates synthetic hard negatives into unsupervised vision transformer pretraining to enhance representation quality. The approach is evaluated on ImageNet and a range of downstream tasks—including transfer learning, image retrieval, copy detection, and image/video segmentation—showing significant performance gains. The synthetic negatives also lead to emergent properties, such as representations that encode explicit semantic information and act as strong classifiers, improving over baselines by up to 11.3%.
The paper proposes a fine‑tuning‑free listwise selector for Text‑to‑SQL systems that replaces traditional learning objectives with inference‑time strategies. It introduces reusable structured memories (MaP‑SQL) that encode mappings from natural language to schema elements, SQL operations, and expected outputs, and uses these memories to evaluate candidate queries. To reduce positional bias, the method aggregates rankings across multiple input permutations, optimizing inference cost through execution results and pointwise scoring. The approach achieves higher selection accuracy, fewer unnecessary comparisons, and outperforms the prior state‑of‑the‑art R^3‑SQL on the BIRD‑dev benchmark while using fewer tokens.
The paper proposes the interlingua hypothesis, suggesting that large language models translate by encoding a source sentence into a latent, task‑agnostic feature space and then decoding a target sentence from that space. Three lines of evidence support this: (1) BLEU variance across language pairs is largely explained by language‑specific competences without pair‑specific interactions; (2) many model components influence both monolingual and translation tasks; and (3) fine‑tuning on monolingual data recovers most translation gains seen with aligned documents. These findings converge to support the hypothesis and point toward new ways to understand and improve LLM translation.
Safin-1 is a new family of foundation models that embeds safety directly into the model’s internal state through memory routing and state evolution. It uses a Memory-Anchor Routing across Context History (MARCH) architecture to maintain structured memory states and selectively retrieve relevant historical information, allowing test‑time adaptation of persistent capability states without altering the backbone. Evaluations show that this routed‑state interface improves safety on downstream tasks while also enhancing general capabilities, long‑context understanding, retrieval, and efficiency.
Maize kernel traits such as row number, kernels per row, and kernel size vary largely for genetic reasons and are consistently associated with regions of the genome that influence yield. Manual measur...
Audio Description (AD) provides spoken narration of visual events during dialogue gaps, making movies accessible to visually impaired audiences. The problem requires determining both what (which visua...
LLM-based evaluators of natural language generation (NLG) quality are widely deployed as scoring tools and as automated training signals, yet the internal procedure by which they assign a rating remai...
Large language models (LLMs) struggle to classify text into taxonomies with many semantically similar labels, as the distinctions are domain-specific and not captured by pre-training. To handle large...
Grounded question answering systems should answer only when the supplied evidence supports the answer. In multi-hop QA, this requirement is difficult because partial evidence can make an unsupported a...
Low-rank adaptation fixes the rank of the update, but it does not identify which parts of a trained write actually carry behavior. We study that question directly and show that behaviorally effectiv...
Process mining (PM) provides a powerful framework for discovering and optimizing operational processes from event data. However, the efficacy of PM techniques is strictly predicated on the availabilit...
Every supervised fine-tuning run forces the same chain of decisions, such as learning rate, batch size, LoRA or full fine-tuning, how many epochs, which optimiser, and what data to feed the model. Eac...
Production LLMs must handle inputs that attempt to override system instructions, bypass safety policies or elicit harmful responses. A common mitigation is a separate guardrail model. Existing reports...
Low-quality face recognition (LQFR) remains challenging due to the difficulty of matching degraded query (probe) images against low-quality (LQ) enrollment (gallery) imagery and the scarcity of traini...
Parameter-efficient fine-tuning is usually framed as a question of how many parameters to update. Under a severe trainable-state budget, however, where those coefficients act is equally consequential....
arXiv:2608.29208v1 Announce Type: cross Abstract: Vision-Language-Action (VLA) models, built upon Vision-Language Models (VLMs), have significantly enhanced robotic capabilities by leveraging interne...
The paper investigates why reinforcement learning with verifiable rewards (RLVR) reduces the diversity of solutions in reasoning tasks. By analyzing the Countdown task, the authors show that RLVR contracts the solution space mainly at the entrance—before the first arithmetic operation—causing a 67% drop in solution coverage. They demonstrate that providing an unselected entrance prefix or applying entrance‑targeted interventions can restore or even improve coverage without harming accuracy.
The paper introduces FAB, an attack that uses meta‑learning to embed dormant adversarial behaviors into large language models (LLMs). These behaviors remain inactive until the model is finetuned by downstream users, at which point the model can exhibit unwanted actions such as unsolicited advertising, jailbreakability, or over‑refusal. FAB is shown to be effective across multiple LLMs and resilient to various finetuning settings.