Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv:2606.22394v3 Announce Type: replace Abstract: Consistency distillation has significantly accelerated diffusion-model inference, but its sampling dynamics remain underexplored. We reveal an asym...
arXiv:2608.30129v1 Announce Type: new Abstract: This work presents $\textbf{Lapis}$, a $\textbf{l}$inear-$\textbf{a}$ttention-based $\textbf{pi}$xel-$\textbf{s}$pace generative framework that achieve...
The paper introduces a curiosity‑driven quantized Mixture‑of‑Experts framework that routes inputs based on Bayesian epistemic uncertainty across heterogeneous experts (BitNet ternary, 1‑16 bit BitLinear, post‑training quantization). On audio classification benchmarks, 4‑bit quantization preserves 99.9 % of full‑precision F1 while achieving 4× compression and 31 % energy savings, and curiosity‑driven routing further improves accuracy and reduces cross‑fold variance by up to 85 %. The routing is self‑organizing, allocating the most uncertain samples to the high‑precision expert, and the method demonstrates statistical parity with full precision across datasets.
arXiv:2608.29088v1 Announce Type: new Abstract: Multimodal question answering remains sensitive to noisy, incomplete, and weakly grounded evidence. Long unstructured contexts can introduce redundancy...
The paper introduces GRKV, a training‑free method for compressing the key‑value cache in long‑context large language models. GRKV uses ridge‑regression to redistribute information from evicted tokens to retained ones, aiming to minimize the difference between compressed‑cache and full‑cache attention outputs. Experiments on LongBench and RULER show that GRKV improves overall performance with minimal overhead compared to other merging methods.
Post‑training quantization of large language models reduces memory usage but can alter social biases in ways that aggregate metrics miss. In a large‑scale study of 50 quantized models on PostTrainingBiasBench, the authors discovered a phenomenon called quantization‑induced bias flipping, where up to 21% of responses switch from biased to unbiased or vice versa, especially for uncertain predictions and stronger quantization (4‑bit vs 8‑bit). These flips lead to asymmetric impacts across demographic groups, with some groups experiencing up to an 18.6% worsening of bias while others improve by 14.1%, resulting in misleadingly neutral overall scores.
arXiv:2608.29891v1 Announce Type: new Abstract: Unsupervised skeleton-based temporal action segmentation is a crucial task for understanding human behavior in long untrimmed sequences. Recent approac...
arXiv:2603.12824v3 Announce Type: replace-cross Abstract: Vision-Language Model (VLM) based retrievers have advanced visual document retrieval (VDR) to impressive quality. They require the same multi...
SpanCalib-VLM is a hybrid system for detecting hallucinated text spans in Vision‑Language Models. It combines a multimodal sequence tagger (XLM‑RoBERTa‑Large + SigLIP) with a fine‑tuned generative VLM (Qwen3.5‑4B‑SHROOM‑SFT) and uses a Union‑Calibrated Fusion strategy to re‑score candidate spans. On the SHROOM‑Visions English evaluation split, the ensemble achieves a Pearson calibration correlation of 0.41, an overall IoU of 0.39, a clean‑response IoU of 0.91, and a detection accuracy of 70.7%.
Context-Aware Interleaved Batching for WhisperX proposes a new batching strategy that combines WhisperX’s fast intra-audio batching with Whisper’s sequential context retention. By using voice activity detection (VAD) to define segment boundaries, the algorithm stabilizes Whisper’s text conditioning and preserves continuous historical context across batched audio segments. Experiments on long‑form audio benchmarks show reduced Word Error Rate and improved proper noun transcription while maintaining high‑throughput inference speeds.
arXiv:2603.16622v2 Announce Type: replace Abstract: Instead of directly distilling a language model, this study addresses the problem of aligning a base model with a target model in distribution by d...
The paper introduces TASPO, a method that transforms privileged information (PI) into outcome‑grounded action credit for language‑model agents. TASPO constructs decision‑applicable PI from verified successful experience, aggregates PI‑induced likelihood shifts at the executable‑action level, and converts relative action support into positive, bounded, mean‑preserving weights on the original trajectory advantage. Experiments on three agentic benchmarks show TASPO improves over GRPO by 10.6% and generalizes better to unseen tasks, while reducing supervision mismatch and stabilizing policy optimization.
arXiv:2608.29099v1 Announce Type: new Abstract: Temperature scaling is a core component of knowledge distillation, yet its role and effect are still not fully understood. Transformed Teacher Matching...
arXiv:2608.28696v1 Announce Type: new Abstract: Visual in-context learning (ICL) with multimodal large language models (MLLMs) is effective for fine-grained visual classification, but each retrieved...
arXiv:2608.30034v1 Announce Type: new Abstract: Two-stage vision pipelines often place an enhancement network before a task network, on the assumption that a cleaner input produces a better output. W...
arXiv:2608.30295v1 Announce Type: cross Abstract: Large language models (LLMs) have demonstrated strong capabilities in handling long-context tasks, but processing such long contexts remains challeng...
arXiv:2608.31102v1 Announce Type: cross Abstract: Industrial post-training is a brownfield regime. Teams inherit a deployed checkpoint and must land targeted improvements under fixed compute and mixt...
arXiv:2608.30510v1 Announce Type: cross Abstract: For provenance research and art market studies, auction catalogs are an essential resource to trace specific objects over time and space. While histo...
arXiv:2608.29027v1 Announce Type: new Abstract: Shrimp disease classification has become an urgent issue due to its significant impact on the import-export output of producing countries, particularly...
arXiv:2512.23649v5 Announce Type: replace-cross Abstract: Humans learn locomotion through visual observation, interpreting visual content first before imitating actions. However, state-of-the-art hum...