LoRA, PEFT, instruction tuning and domain adaptation — adapting a pretrained model without paying to train one.
arXiv:2602. 00884v2 Announce Type: replace Abstract: Neural operators have shown promise in learning solution maps of partial differential equations (PDEs), but they often struggle to generalize when test inputs lie outside the training distribution, such as novel initial conditions, unseen PDE coefficients or unseen physics.
arXiv:2608. 09260v1 Announce Type: cross Abstract: Large language models (LLMs) have advanced Text-to-SQL by enabling natural language interfaces to databases without task-specific fine-tuning.
arXiv:2608. 07567v1 Announce Type: cross Abstract: Functional near-infrared spectroscopy (fNIRS) is a promising modality for autism spectrum disorder (ASD) classification, yet existing approaches assume temporally aligned evaluation.
arXiv:2608. 09119v1 Announce Type: new Abstract: We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13.
arXiv:2608. 09124v1 Announce Type: new Abstract: Temporal decisions in language-model systems often depend on both symbolic task state and elapsed wall-clock time, such as cache expiration, job completion, quota resets, deadlines, or stale sessions.
arXiv:2607. 28069v2 Announce Type: replace Abstract: Long-context retrieval and agentic workloads repeatedly reuse the same documents under changing instructions, histories, and document orders.
arXiv:2608. 08451v1 Announce Type: cross Abstract: Harmful chat dialogues are ever-shifting through type-shifting and lexical evasion, yet we find they share invariant principles, i.
arXiv:2608. 09633v1 Announce Type: cross Abstract: Face presentation attack detection (PAD) aims to reliably detect a wide range of presentation attacks.
arXiv:2608. 09880v1 Announce Type: cross Abstract: Financial prediction typically relies on task-specific regression, ranking, or policy heads, separating the language model from the numerical object ultimately evaluated.
Transforming table-form documents into machine-processable records requires recovering not only their visible content but also the multilevel structure that organizes it. However, existing benchmarks evaluate either holistic document outputs or conventional table grids, and their aggregate scores provide little insight into where structural failures occur.
Program evolution can measure whether a mutation helped, but it rarely controls how far the mutation moves in behavior space. Syntactic edit size is an unreliable proxy: a small code change can alter nearly every action, while a larger rewrite can preserve the same execution trace.
Large language models (LLMs) have advanced code generation, where executable feedback provides a more reliable learning signal than textual imitation alone. Hardware verification is an important application of code generation and accounts for a substantial fraction of modern chip design effort, with high-coverage testbench stimulus generation as a key task.
Multimodal Large Language Models (MLLMs) have shown strong multimodal instruction-following ability, but adapting them to diverse visual-language domains typically assumes centralized data access and costly joint training. This is restrictive when data is distributed across private, domain-specific, or permission-limited clients.
GUI agents are shifting from metadata-dependent large language models to purely visual multimodal large language models (MLLMs) that operate directly on screenshots. The core task, GUI grounding, requires translating abstract user instructions into precise element coordinates.
Long-horizon future-frame prediction is important for autonomous driving, traffic surveillance, and intelligent transportation systems, yet remains challenging due to temporal ghosting, geometry drift, and inconsistent object motion. Recent latent video diffusion models have achieved impressive visual quality, but directly applying them to structured traffic scenes often leads to unstable geometry and degraded temporal coherence over extended horizons.
Self-evolving methods improve the capabilities of LLM agents by sampling trajectories from the underlying LLMs and learning from these trajectories. However, these methods struggle to learn beyond the inherent capability boundary of the agents, since the agents cannot sample correct trajectories on difficult examples for further improvements.
Large language model-based multi-agent systems have recently shown strong potential for complex, long-horizon tasks. However, existing methods mainly rely on coarse prompt-level differentiation without parameter adaptation for diverse subtasks, resulting in insufficient inter-agent heterogeneity and limited specialized capability that bottleneck performance on tasks with complex requirements.
Omnimodal language models (OLMs) enable unified audio-visual understanding, but processing long joint token sequences makes inference computationally prohibitive. While recent token compression methods attempt to alleviate this burden, compressing modalities in isolation often destroys the temporal cross-modal anchors necessary for coherent reasoning.
We introduce Motif 3, a decoder-only Mixture-of-Experts language model with 314 billion total parameters and 13. 2 billion activated per token.
arXiv:2603. 27435v2 Announce Type: replace-cross Abstract: Large language models (LLMs) are increasingly being used to generate comprehensive, knowledge-intensive reports.