LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2604.18364v2 Announce Type: replace Abstract: Generating programmatic animation using libraries such as Manim presents unique challenges for Large Language Models (LLMs), requiring spatial reas...
arXiv:2509.04183v3 Announce Type: replace-cross Abstract: The growing demand for scalable psychological counseling highlights the need for high-quality, privacy-compliant data, yet such data remains...
arXiv:2505.22635v2 Announce Type: replace-cross Abstract: A common approach for teaching large language models (LLMs) to reason is to train on chain-of-thought (CoT) traces of in-distribution reasoni...
The paper compares five machine unlearning (MU) methods—NegGrad, Fine‑Tuning (FT), Random Labeling (RL), SalUn, and MUNBa—on noisy‑label correction across CIFAR‑10, CIFAR‑100, and Food‑101N. Results show that the best MU strategy depends on the noise type: FT works well for most closed‑set noise, RL and SalUn are robust and nearly match retraining accuracy under instance‑dependent noise, while MUNBa excels only under extreme symmetric noise. In open‑set noise, retraining on the cleaned data actually hurts performance, indicating that approximating retraining is not suitable in that regime, yet all MU methods still achieve near‑retraining accuracy on Food‑101N with much lower runtime.
arXiv:2608.29326v1 Announce Type: cross Abstract: Positive psychology dialogue aims to support emotional distress and positive resource building, requiring models to produce not only empathetic repli...
arXiv:2503.00030v3 Announce Type: replace-cross Abstract: Self-play-based policy optimization has emerged as an effective approach for fine-tuning large language models (LLMs), formulating preference...
The paper investigates how to choose language models (teachers) for generating multilingual synthetic data used to fine‑tune smaller student models. By evaluating 10 teacher models across six diverse languages and training 240 students, the authors find that teacher effectiveness is not driven by model size but by data qualities such as prompt diversity, length, and fluency, which explain most of the variance in student performance. Practical guidelines are offered, including matching teacher and student families and using translated prompts to improve outcomes for low‑resource languages.
Motus2 is a self‑evolving general world model designed for dexterous manipulation. It integrates a shared‑weight model that offers three control interfaces—a policy, a simulator, and an evaluator—forming a closed decision‑and‑learning loop for policy improvement. The system scales both model size and data, progressing from large‑scale monocular egocentric data to synchronized stereo data and robot‑domain adaptation, while also incorporating tactile feedback and a biomimetic platform with dual arms and hands.
EvoLen is a tokenization method for DNA language models that incorporates evolutionary information to prioritize functional sequence patterns such as regulatory motifs. It groups DNA sequences by cross-species evolutionary signals, trains separate BPE tokenizers for each group, merges vocabularies with a rule that favors preserved patterns, and uses length-aware decoding with dynamic programming. Experiments show EvoLen better preserves functional motifs, differentiates genomic contexts, and aligns with evolutionary constraints while matching or surpassing standard BPE on various DNALM benchmarks.
arXiv:2602.11166v2 Announce Type: replace-cross Abstract: Parameter-efficient fine-tuning (PEFT) methods are widely used to adapt large language models (LLMs) to downstream tasks and are often assume...
arXiv:2603.02465v2 Announce Type: replace-cross Abstract: Machine learning-based wildfire detection has advanced significantly using deep learning models trained on large wildfire image and video dat...
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 a diagnostic framework to disentangle the effects of character profile axes—Familiarity, Structure, and Disposition—on large language model role‑playing agents. Experiments on 211 personas and five LLMs show that Familiarity and Structure have little impact, whereas Disposition, particularly immoral traits, consistently degrades performance. The authors propose Field‑Aware Contrastive Decoding (FACD), a training‑free method that mitigates this performance gap without harming moral‑character performance.
The paper investigates whether fine‑tuning improves how language models use supplied Bangladeshi legal text in bilingual question‑answering. Using a hierarchy‑preserving statutory corpus, 2,165 fine‑tuning examples, and a 150‑item control set, the authors evaluate six instruction‑tuned models with multiple LoRA seeds, separating scoring, retrieval, and model effects. Results show that while fine‑tuning can boost overall accuracy, it does not increase the models’ reliance on the governing provision, highlighting the need to disentangle scorer, retriever, and model contributions in legal adaptation studies.
arXiv:2604.27426v2 Announce Type: replace-cross Abstract: Local fine-tuning datasets routinely contain sensitive secrets such as API keys, personal identifiers, and financial records. Although "local...
The paper investigates how different forms of compressed chain‑of‑thought (CoT) reasoning—Explicit, Composed, and Implicit—affect large language model (LLM) performance after supervised fine‑tuning (SFT). Using a synthetic compositional reasoning task, the authors show that coarser CoT requires more SFT data, that Composed and Implicit CoT benefit more from data scaling (with Composed also benefiting from repetition), and that reinforcement learning with verifiable rewards (RLVR) can decompose compressed steps learned during SFT. Additionally, unidirectional CoT ordering improves generalization on longer sequential tasks.
arXiv:2606.17446v2 Announce Type: replace-cross Abstract: Simulation enables scalable robot data collection, but raw 3D assets provide only geometry, lacking the semantic, interactive, and physical k...
arXiv:2509.06422v2 Announce Type: replace Abstract: Video camouflaged object detection (VCOD) is challenging due to dynamic environments. Existing methods face two main issues: (1) SAM-based methods...
arXiv:2608.29579v1 Announce Type: new Abstract: Chaotic time series forecasting is a challenging task due to its sensitivity to initial conditions and long-term unpredictability. Traditional methods...
arXiv:2608.31013v1 Announce Type: new Abstract: Designing models that generalize effectively in low- to medium-data regimes remains a primary challenge in medical machine learning, particularly for p...