LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2610.07713v1 Announce Type: new Abstract: Surface electromyography (sEMG) provides a wearable, noninvasive interface to neuromuscular activity for movement decoding and human-computer interacti...
The paper investigates how exporting ternary language models (BitNet, Falcon‑E, BitCPM) through a bf16 cast step can introduce significant discrepancies between the fine‑tuned latent weights and the deployed ternary codes. In three lab pipelines, the authors find that fp32 quantization of shipped latents disagrees with the deployed codes on up to 1.77% of codes, and that the export step can drastically reduce strict accuracy on GSM8K (e.g., from 58.79% to 0.78% for Falcon‑E‑1B‑Base). They propose two compatibility remedies—directly writing the training quantizer’s codes or adjusting bf16 inputs—to meet a 4‑point strict‑accuracy non‑inferiority criterion across all models.
Reconstructing 3D Computed Tomography (CT) images from a few X-ray projections is a highly ill-posed inverse problem due to the loss of volumetric information. We propose PhyDiCT, a training-free fram...
Enterprise generative AI applications require robust safety mechanisms that can accommodate diverse risk postures, evolving policies, and varying latency constraints. Current guardrail solutions often...
Flow policies have become a standard policy class for learning robot behaviors from demonstrations, but reinforcement learning is still critical for improving pre-trained flow policies or learning the...
High-beam-count LiDAR sensors are costly, yet many perception pipelines require dense angular sampling. Using a pretrained Stable Diffusion model as the backbone, we fine-tune a LiDAR-conditioned dept...
Automatic Speech Recognition (ASR) systems often show uneven performance across demographic groups, and errors can be especially difficult to address for speakers belonging to multiple demographic gro...
Large-scale self-supervised pretraining has reshaped modern machine learning, substantially advancing the ability of language and vision models to generalize across downstream tasks. While deep learni...
Diffusion language models (dLLMs) have emerged as a promising alternative to autoregressive (AR) language models, offering flexible token-update orders and parallel decoding. Recent dLLMs are often in...
LLM tool-use agents operate in dynamic environments where many actions carry operational risk. However, most safety mechanisms react only after errors manifest. Existing pre-emptive approaches either...
Multi-agent systems (MAS) powered by large language models have shown strong performance across code generation, mathematical reasoning, and question answering. However, existing methods for automatin...
Surface electromyography (sEMG) provides a wearable, noninvasive interface to neuromuscular activity for movement decoding and human-computer interaction. Population-scale decoding remains difficult b...
S2PD: Serial-to-Parallel Diffusion for Physically and Logically Consistent Video Generation introduces a hybrid diffusion approach that first applies autoregressive diffusion at high noise levels and then switches to parallel diffusion at low noise levels. This method coordinates interdependent events to produce valid state transitions while reducing sampling time compared to fully serial generation. Implemented with a pixel‑space diffusion transformer and a LoRA‑fine‑tuned pretrained video model, S2PD outperforms bidirectional baselines in rule adherence and achieves greater temporal stability and sampling efficiency across games, physical simulations, and real video.
T-Search is an open-weight agentic retriever designed for hard multi-step search tasks. It performs bounded multi-round searches over a fixed corpus, returning ranked evidence chunks with brief justifications, while allowing the answer generation component to be swapped without retraining. Trained on synthetic search tasks and evaluated on seven English and Russian benchmarks, it achieves 56.0 Recall@10 with one rollout and 61.3 with three fused rollouts, surpassing larger open models.
The paper explores how prior-data fitted networks (PFNs) can be adapted for anomaly detection in tabular data. Using frozen TabPFN features, the authors show that scoring samples by nearest-neighbor distance in feature space yields strong results, and they identify optimal layers and extraction procedures. They further improve performance by fine‑tuning the model on a reference set, achieving higher AUROC on the ADBench benchmark with both a fine‑tuning‑free (ZEN) and a fine‑tuned (FOCUS) approach.
The paper introduces DUCB-OGD, an algorithm that couples a Discounted Upper‑Confidence‑Bound sampler with Online Gradient Descent to address dynamic minimax regret in robust large‑language‑model post‑training. It operates under instantaneous mini‑batch‑only bandit feedback, tracking worst‑source performance without re‑evaluating historical data. Experiments on fine‑tuning, preference optimization, and reinforcement learning demonstrate that DUCB‑OGD improves worst‑group robustness with negligible computational overhead.
The paper presents a lightweight on‑device personalization method for ECG monitoring called prototype‑only head adaptation. It freezes a small 1‑D CNN feature extractor and adapts only class prototypes in a 32‑dimensional embedding space, eliminating costly back‑propagation and requiring only a single forward pass per support beat. The approach boosts inter‑patient macro‑F1 scores from 0.635–0.646 to 0.731–0.797 across 1/5/10‑shot scenarios and runs efficiently on a PSoC 6 microcontroller with minimal memory and latency.
The paper introduces ARRO, a reinforcement‑learning framework that enforces minimal‑change editing by auditing source images, instructions, and edited outputs for unimplemented and unintended changes. Using a vision‑language reward model and a group‑level rubric, ARRO achieves higher EditScore on multiple benchmarks and reduces off‑target pixel changes by 8.4% on FLUX.1 Kontext‑dev. The approach eliminates the need for per‑instruction human annotations and demonstrates strong performance across several evaluation sets.
The paper demonstrates that off‑policy merging, called grafting, outperforms on‑policy self‑distillation for continual learning. Grafting learns updates on an earlier donor checkpoint, scales the update, and optionally masks sensitive directions, thereby reducing interference with existing capabilities. Across various continual learning scenarios, grafting achieves better new‑task and old‑task performance without costly on‑policy sampling.
The paper introduces a game-theoretic approach to text revision, treating token positions as players and vocabulary items as actions, with utilities based on a language model’s log conditional probability. It shows that Nash equilibria can yield exponentially higher likelihoods than autoregressive outputs as sequence length increases, and proposes Nash decoding, an algorithm that finds an ε-Nash equilibrium in O(1/ε) time. Experiments on CLAPNQ, PubMedQA, and CoQA demonstrate that equilibria derived from masked language models achieve higher F1 and ROUGE scores than autoregressive models, up to 18× larger, without fine-tuning, though with extra test-time computation.