Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2608. 01804v1 Announce Type: new Abstract: Post-training large language models (LLMs) via reinforcement learning (RL) has significantly advanced code generation capabilities.
arXiv:2606. 21994v2 Announce Type: replace Abstract: On-policy distillation (OPD) improves reasoning models by applying dense teacher supervision on student-sampled trajectories.
arXiv:2608. 01247v1 Announce Type: cross Abstract: Query-agnostic KV cache eviction compresses a context once and reuses the resulting cache for arbitrary future queries, but performance can collapse under tight budgets.
arXiv:2608. 01821v1 Announce Type: cross Abstract: Diffusion vision-language models (dVLMs) iteratively denoise masked responses while conditioning each denoising step on visual evidence, making visual conditioning a substantial recurring inference cost.
arXiv:2608. 00533v1 Announce Type: cross Abstract: Large Language Models have achieved substantial progress in reasoning capabilities.
arXiv:2608. 01460v1 Announce Type: new Abstract: Conformal prediction (CP) is a distribution-free framework for uncertainty quantification that has recently been adapted to large language models (LLMs), providing prediction sets with finite-sample coverage guarantees under exchangeability.
arXiv:2608. 01303v1 Announce Type: new Abstract: Symbolic alpha factor discovery can score a completed expression, but it provides no direct label for the structural decisions that produced it.
arXiv:2608. 02222v1 Announce Type: new Abstract: One-shot federated learning (OSFL) has emerged as a promising collaborative model learning framework with only a single round of communication, offering significant advantages in communication efficiency and privacy preservation.
arXiv:2608. 01651v1 Announce Type: cross Abstract: Hybrid-attention large language models combine full attention with recurrent linear attention to reduce long-context inference costs, yet their autoregressive decoding remains memory-bound.
arXiv:2608. 01597v1 Announce Type: new Abstract: Search-augmented LM agents are typically trained with a binary exact-match reward, which throws away most of what a failed trajectory tells us about why it failed.
arXiv:2604. 01622v2 Announce Type: replace Abstract: Diffusion language models (DLMs) enable parallel, non-autoregressive text generation, yet existing DLM mixture-of-experts (MoE) models inherit token-choice (TC) routing from autoregressive systems, leading to load imbalance and rigid computation allocation.
arXiv:2608. 01285v1 Announce Type: new Abstract: The continued development of LLMs toward persistent and adaptive intelligence increasingly requires long-term memory mechanisms that preserve and reuse information across interactions.
arXiv:2608. 01023v1 Announce Type: new Abstract: We present Caliber, an output-perturbation defense against model extraction that formulates noise selection as a calibration problem: how much the defense degrades the supervision signal used to train a surrogate, and the provable per-input query cost of recovering the clean logits.
arXiv:2608. 00859v1 Announce Type: new Abstract: Kolmogorov--Arnold Networks (KANs) replace scalar edge weights with learnable univariate functions parameterized by multiple basis coefficients.
arXiv:2602. 02599v4 Announce Type: replace Abstract: Long-context inference in large language models (LLMs) is bottlenecked by the memory and compute of the key-value (KV) cache.
arXiv:2608. 00220v1 Announce Type: new Abstract: We show that on-policy reinforcement learning with verifiable rewards (RLVR) can improve the current objective while making successful behaviors for later objectives too rare to sample and reinforce.
arXiv:2601. 21369v2 Announce Type: replace Abstract: Recent studies of federated graph foundational models (FedGFMs) break the idealized and untenable assumption of having centralized data storage to train graph foundation models, and accommodate the reality of distributed, privacy-restricted data silos.
arXiv:2505. 20894v2 Announce Type: replace Abstract: Despite recognized limitations in modeling long-range temporal dependencies, Human Activity Recognition (HAR) has traditionally relied on a sliding window approach to segment labeled datasets.
arXiv:2608. 00737v1 Announce Type: new Abstract: Hard-constrained recurrent physics-informed networks (HRPINNs) embed known dynamics inside a recurrent numerical integrator and restrict a neural branch to learning only the residual dynamics that the first-principles model does not capture.
arXiv:2606. 14581v4 Announce Type: replace Abstract: High-throughput experimentation can evaluate many reaction conditions, yet combinatorial condition spaces still exceed the available experiment budget.