Leaderboards, eval harnesses and ablations — the contested business of deciding which model is actually better.
arXiv:2608. 01679v2 Announce Type: replace Abstract: Persistent memory allows (self-evolving) LLM agents to adapt across tasks by consolidating heterogeneous interaction histories into reusable facts, preferences, observations, and rules.
arXiv:2608. 03579v1 Announce Type: cross Abstract: Modern multi-tenant Low-Rank Adapters (LoRAs) serving systems concurrently host tens to hundreds of LoRA adapters.
arXiv:2608. 03432v1 Announce Type: new Abstract: Refurbishment-based noisy-label learning mixes an observed label with a model-derived pseudo target, typically using one sample-wise cleanliness score to control both branches.
arXiv:2608. 03565v1 Announce Type: new Abstract: While modern tabular learners excel at capturing statistical patterns, they frequently operate in a semantic vacuum, treating textual features as discrete symbols, ignoring the rich semantics inherent in feature names or cell entries.
arXiv:2608. 03028v1 Announce Type: new Abstract: Applying a valid medication-safety rule when its patient-specific conditions are not met can produce an incorrect decision.
arXiv:2608. 03161v1 Announce Type: new Abstract: Lecture videos distribute knowledge across speech, slide text, diagrams, equations, and presentation order, which transcript-only retrieval does not fully preserve.
arXiv:2608. 03330v1 Announce Type: new Abstract: This thesis addresses fundamental challenges in traffic scene prediction for autonomous driving by introducing robust and computationally efficient models based on polynomial representations.
arXiv:2608. 03839v1 Announce Type: new Abstract: Training-free speculative decoding drafts by matching an exact suffix of the context against a pool of earlier context.
arXiv:2511. 15339v3 Announce Type: replace-cross Abstract: Automotive telemetry data exhibits slow drifts and fast spikes, often within the same sequence, making reliable anomaly detection challenging.
arXiv:2608. 02833v1 Announce Type: cross Abstract: Chart question answering (CQA) requires multimodal large language models (MLLMs) to integrate visual comprehension with logical reasoning, yet current models struggle with accurate visual grounding and coherent reasoning chains.
arXiv:2608. 03401v1 Announce Type: cross Abstract: Large language models often reason at length before answering, increasing cost and latency.
arXiv:2608. 03691v1 Announce Type: cross Abstract: Multimodal large language models (MLLMs) are increasingly used to translate webpage screenshots into front-end code, but repeated UI patterns may sway them toward visually incorrect yet pattern-consistent outputs.
arXiv:2608. 03860v1 Announce Type: cross Abstract: We introduce SciRet, a compute-aware empirical study of retrieval-augmented generation for scientific question answering over CORD-19.
arXiv:2512. 01370v2 Announce Type: replace-cross Abstract: Diffusion-based solvers for partial differential equations (PDEs) are often bottle-necked by slow gradient-based test-time optimization routines that use PDE residuals for loss guidance.
arXiv:2604. 18933v2 Announce Type: replace-cross Abstract: Robotic manipulation tasks exhibit varying memory requirements, ranging from Markovian tasks that require no memory to non-Markovian tasks that demand in-context memorization of historical information within a single trial or in-context adaptation based on the outcomes of multiple past trials.
arXiv:2608. 01269v2 Announce Type: replace-cross Abstract: Hierarchical Graph Retrieval-Augmented Generation (GraphRAG) organizes corpus knowledge at multiple levels of granularity, yet fixed context construction may fail to translate these multi-resolution representations into a context suited to the current query.
arXiv:2608. 03045v1 Announce Type: new Abstract: We consider grey-box optimization problems where the decision variables naturally partition into black-box variables (as arguments to an expensive black-box function) and white-box variables, governed by a set of explicit, closed-form equations that also depend on the output of the black-box function.
arXiv:2608. 03259v1 Announce Type: cross Abstract: As time-series foundation models have emerged, the need for benchmarks that can evaluate their forecasting ability in meaningful ways has become increasingly important.
Long-context large language models (LLMs) are increasingly deployed in real-world applications, yet self-attention remains a major efficiency bottleneck -- especially during decoding -- due to the necessity of repeatedly processing ever-growing key-value (KV) caches. Existing sparse attention reduce computation by attending to fewer KV pairs, but often suffer from substantial accuracy degradation, require additional training, or rely on expensive hashing.
Mixture-of-Experts (MoE) models enable model scaling while maintaining low inference-time compute by activating only a subset of experts per token. However, conventional routing relies on a fixed top-k selection, forcing the model to spend the same compute regardless of how many experts are relevant.