LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2608. 05446v1 Announce Type: new Abstract: Long-horizon LLM agents increasingly rely on external execution support to maintain state, track progress, invoke tools, verify outcomes, and reuse experience across interactions.
arXiv:2608. 05255v1 Announce Type: cross Abstract: Retail investors lack access to the kind of personalized, tax-aware portfolio management that institutional clients take for granted -- existing robo-advisors use static, rule-based allocation, and institutional-grade systems require account minimums and technology stacks unavailable to individual investors.
arXiv:2608. 05165v1 Announce Type: cross Abstract: Speech Emotion Recognition (SER) in low-resource languages remains a challenging problem due to limited labeled data.
arXiv:2608. 05734v1 Announce Type: new Abstract: Subliminal Learning (SL) is a surprising type of generalization displayed by modern language models.
arXiv:2608. 06253v1 Announce Type: new Abstract: Metabolomics knowledge is distributed across heterogeneous resources and remains difficult to translate into predictive representations.
arXiv:2608. 06259v1 Announce Type: new Abstract: Reaction yield prediction remains challenging because labeled data are scarce and reaction space is both combinatorially large and sparsely populated, limiting the generalization of existing reaction representations.
arXiv:2608. 05471v1 Announce Type: cross Abstract: Prenatal ultrasound imaging is key for assessing fetal health, but AI progress is limited by scarce, privacy-restricted, and hard-to-annotate datasets.
arXiv:2608. 06246v1 Announce Type: new Abstract: Post-training adaptation has become central to modern machine learning practice and includes techniques such as retraining, fine-tuning, parameter-efficient adaptation, alignment, retrieval augmentation, model editing, unlearning, calibration, and Multimodal Instruction Tuning.
arXiv:2605. 04970v3 Announce Type: replace-cross Abstract: Modern LLMs show mastery over an ever-growing range of skills, as well as the ability to compose them flexibly.
arXiv:2605. 20247v2 Announce Type: replace-cross Abstract: Catastrophic forgetting remains a major obstacle to continual learning in large language models (LLMs) and vision--language models (VLMs).
arXiv:2608. 06046v1 Announce Type: cross Abstract: AI training workloads are growing rapidly, making their time, energy, and infrastructure costs increasingly important.
arXiv:2608. 05164v1 Announce Type: cross Abstract: Independently trained large language models may develop shared internal representations of semantic concepts despite architectural differences -- but whether this geometric similarity has functional consequences for cross-model behavioural control remains untested.
arXiv:2511. 17852v3 Announce Type: replace Abstract: Transformers can acquire Chain-of-Thought (CoT) capabilities to solve reasoning tasks via fine-tuning.
arXiv:2608. 05168v1 Announce Type: new Abstract: Large language models often fail on reasoning tasks despite possessing the capability to solve them.
arXiv:2608. 05571v1 Announce Type: new Abstract: Retrieval-augmented forecasting promises to adapt frozen Time Series Foundation Models (TSFMs) to new domains without fine-tuning, but recent methods typically rely on learned fusion modules, i.
arXiv:2608. 05891v1 Announce Type: new Abstract: Mobile GUI agents can operate apps through pixel perception and touch actions, making them a promising interface for collecting and improving long-horizon mobile interaction policies.
arXiv:2608. 05253v1 Announce Type: new Abstract: Quantized orthogonal fine-tuning (qoft) enables parameter-efficient adaptation of low-bit language models by learning structured activation rotations before frozen quantized weights.
arXiv:2608. 06107v1 Announce Type: new Abstract: Machine learning offers a promising avenue to accelerate physical simulations by replacing computationally expensive traditional Partial Differential Equation (PDE) solvers with fast, differentiable surrogate models.
arXiv:2608. 05813v1 Announce Type: new Abstract: Personalizing language models (LMs) to individual user preferences is essential for aligning responses with diverse goals and backgrounds.
arXiv:2608. 05975v1 Announce Type: cross Abstract: In this paper, we present TRACE (Tokenized Robust Attention for Contact-Aware Estimation), an end-to-end learned proprioceptive odometry estimator for legged robots under unreliable contact conditions.