Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
Recent work on distillation transfers the capabilities of large models to smaller ones often by updating the latter's parameters, through teacher forcing, on-policy distillation, and related training-time methods. In this paper, we ask whether such transfer can instead occur at test time.
Use this plain-text version for the arXiv abstract field: Learned image compression (LIC) models achieve strong rate-distortion performance but are hindered by high computational complexity and encoding-decoding mismatches across heterogeneous hardware platforms. Uniform fixed-precision quantization alleviates these issues but suffers severe quality degradation at low bit widths because it ignores differences in the quantization sensitivities of individual layers.
Boosted decision trees (BDTs) are widely used in latency-critical applications, but efficient hardware deployment remains challenging. Existing designs often rely on uniform or manually tuned fixed-point formats, which can introduce unnecessary hardware cost or accuracy loss.
Small Language Models (SLMs) have emerged as a more efficient alternative to traditional Large Language Models (LLMs), offering promising potential in resource-constrained scenarios. Existing approaches to building SLMs typically follow two paths: training compact models from scratch, or compressing larger pre-trained models using methods such as pruning, quantization, or distillation.
Aggressive quantization disproportionately harms multilingual capability: in the sub-4B INT3 GPTQ regime, we measure 2-4x larger perplexity degradation on non-English languages than on English. We propose Language-Conditional Dequantization (LCD), a post-hoc method that attaches per-language rank-2 LoRA corrections to the linear layers of an already-quantized model, adding 0.
Diffusion Large Language Models (dLLMs) have emerged as a competitive alternative to autoregressive language models, offering the potential for substantially faster inference through parallel decoding. Existing parallel decoding schedulers typically commit positions only after they meet a per-position criterion, overlooking how early commitments may benefit subsequent decoding.
arXiv:2507. 06849v3 Announce Type: replace-cross Abstract: Neural network (NN)-based Digital Predistortion (DPD) improves linearization for wideband radio frequency (RF) power amplifiers (PAs) but often increases the complexity of the digital back-end.
arXiv:2608. 10524v1 Announce Type: cross Abstract: Driven by the rapid advancement of vision-language representation learning, Text-based Image Retrieval (TBIR) has made notable progress.
arXiv:2608. 10528v1 Announce Type: cross Abstract: Anchor-based pointwise LLM reranking scores each candidate against a shared reference passage to recover cross-document context at pointwise cost.
arXiv:2608. 10290v1 Announce Type: cross Abstract: Comprendia is an Eclipse plugin that integrates structural dependency visualization with LLM-powered code explanation on a shared interactive graph for Java program comprehension.
arXiv:2608. 10545v1 Announce Type: cross Abstract: Edge LLMs must preserve inference continuity when a user hands over between edge nodes, requiring key-value (KV) cache transfer to the target node.
arXiv:2608. 10430v1 Announce Type: cross Abstract: Large Language Models (LLMs) deployed as AI agents frequently exhibit user specification-grounding failures, executing hallucinated, undesired actions to force a resolution rather than expressing uncertainty.
arXiv:2602. 02035v2 Announce Type: replace-cross Abstract: Multi-agent reinforcement learning systems deployed in real-world robotics applications face severe communication constraints that significantly impact coordination effectiveness.
arXiv:2608. 10523v1 Announce Type: cross Abstract: \texttt{TensorSketch} by~\cite{pham2013fast,kar2012random} provides efficient sketching algorithms for high-dimensional polynomial kernels $\vec{x}^{\otimes p} \in \R^{d^p}$.
arXiv:2508. 03611v3 Announce Type: replace-cross Abstract: This paper presents Astrolabe, a randomized prediction-guided scheduler for one-shot request dispatch in multi-instance large language model (LLM) serving.
arXiv:2608. 10214v1 Announce Type: new Abstract: Do large language models contain domain-specific parametric shells: concentrated, causally necessary neuron populations whose removal selectively degrades a target domain while sparing others?
arXiv:2608. 11045v1 Announce Type: new Abstract: ReRound (Reconstructive Rounding) is a post-training quantization method that addresses the midpoint ambiguity inherent in standard round-to-nearest (RTN) schemes when quantizing weights near the centers of quantization intervals.
arXiv:2608. 10775v1 Announce Type: new Abstract: Computer-using agents can perceive rich software interfaces, yet their decisions often lack visual procedural memory: they may recognize individual controls without identifying which familiar workflow is active, which control matters next, or what evidence would confirm progress.
arXiv:2608. 10137v1 Announce Type: cross Abstract: Grammar Constrained Decoding (GCD) forces Language Models (LMs) to produce syntactically valid outputs by masking out non-conforming tokens at each step.
arXiv:2601. 10129v2 Announce Type: replace-cross Abstract: Current multimodal latent reasoning often relies on external supervision (e.