LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2608. 14015v1 Announce Type: cross Abstract: Understanding tens-of-minutes surgical videos requires long-horizon temporal reasoning, answering what happens before, after, or across stages of a procedure by grounding the question in visual evidence spread across time.
arXiv:2608. 13937v1 Announce Type: cross Abstract: Smart manufacturing processes are often installed with a large number of sensors, imaging devices and computers, which not only enable instant communication across various modules of a production system but also aid in intelligent manufacturing management.
arXiv:2608. 14212v1 Announce Type: new Abstract: As large language models enter professional domains, they must satisfy domain constraints, include critical evidence, and provide complete reasoning rather than merely produce fluent responses.
arXiv:2608. 14149v1 Announce Type: new Abstract: Recent training-free post-training quantization methods restore model accuracy through closed-form residual compensation.
arXiv:2608. 14094v1 Announce Type: cross Abstract: Cloud-local LLM inference systems have the potential to use the reasoning capability of large cloud models while protecting sensitive user data on personal devices.
arXiv:2607. 28125v2 Announce Type: replace-cross Abstract: Numerous unsupervised domain adaptation (UDA) algorithms exist, but for clinical practice, selecting the best-suited one along with proper hyperparameters often remains unclear, as the unlabeled deployment (target) domain prevents direct evaluation.
arXiv:2608. 14492v1 Announce Type: new Abstract: The Muon optimizer shows clear benefits versus alternatives when pretraining neural networks.
arXiv:2608. 02345v2 Announce Type: replace-cross Abstract: A/B testing remains the standard for rolling out new features in the technology industry.
arXiv:2608. 14089v1 Announce Type: new Abstract: Safety classifiers deployed with large language models often fail for two reasons: their decisions reflect the policy learned during training rather than the deployer's desired policy, and their performance degrades as deployment traffic evolves.
arXiv:2608. 13566v1 Announce Type: cross Abstract: Post-training papers, model cards, and blog posts often treat scores on a small set of coding benchmarks (e.
arXiv:2603. 09868v2 Announce Type: replace Abstract: Accurately quantifying terrestrial carbon exchange is essential for climate policy and carbon accounting, yet models must generalize to ecosystems underrepresented in sparse eddy covariance observations.
arXiv:2608. 14414v1 Announce Type: new Abstract: Cytometry measures the complex characteristics of single cells (e.
arXiv:2608. 13833v1 Announce Type: cross Abstract: Conversational advertising aims to deliver useful ads within multi-turn assistant interactions.
arXiv:2608. 13597v1 Announce Type: cross Abstract: Coverless image steganography (CIS) synthesizes a stego image rather than modifying an existing cover image, enabling authorized recipients to reconstruct the original secret image from the stego.
arXiv:2608. 13926v1 Announce Type: new Abstract: Large language models have made natural language interfaces to databases (NLIDB) newly credible, but LLM text-to-SQL systems fail in a way that matters for deployment: a hallucinated column or a mis-aggregated total yields a fluent wrong answer, indistinguishable at the point of use from a right one.
arXiv:2608. 14022v1 Announce Type: cross Abstract: Action-conditioned video world models require low-latency causal generation and reliable responses to game-native controls.
arXiv:2604. 05379v2 Announce Type: replace-cross Abstract: The sequential recommendation (SR) task aims to predict the next item based on users' historical interaction sequences.
arXiv:2608. 14264v1 Announce Type: cross Abstract: Model merging combines trained models directly in weight space, offering a compute-efficient alternative to additional fine-tuning.
arXiv:2608. 14152v1 Announce Type: new Abstract: Recent advances in large language models (LLMs) have reshaped semantic analysis.
arXiv:2608. 14221v1 Announce Type: new Abstract: Autoformalization is commonly framed as translating natural-language mathematical statements into machine-verifiable formal languages such as Lean 4.