arXiv AI
Jul 29
TabRank: Chain-of-Thought Distillation for Table Re-Rankers
arXiv:2607. 25182v1 Announce Type: cross Abstract: The ability to retrieve relevant tables for answering questions is a key task for structured information retrieval.
Inference efficiency
Quantization, distillation, pruning and serving work aimed at the same accuracy for less memory, latency and money.
arXiv AI
Jul 29
A Cost-Effective Multimodal LLM Reasoning Framework for Question Answering over Irregular Clinical Time Series
arXiv:2607. 25947v1 Announce Type: new Abstract: Question answering (QA) over irregular clinical time series (ICTS) plays a pivotal role in a wide range of healthcare applications.
arXiv AI
Jul 29
GLIDE: Guided Layerwise Hybrid Attention for Efficient LLM Inference
arXiv:2607. 24788v1 Announce Type: new Abstract: As Large Language Models scale to increasingly long contexts, the memory I/O and computational overhead of the Key-Value (KV) cache during decoding emerges as the primary throughput bottleneck.
arXiv AI
Jul 29
Penelope: Localized Latent Recurrence for Efficient Structured Reasoning
arXiv:2607. 25915v1 Announce Type: new Abstract: Complex structured reasoning tasks often require additional computation, yet current language models obtain it mainly by increasing parameter scale or by serializing intermediate steps as chain-of-thought (CoT) tokens.
arXiv AI
Jul 29
At-the-Roofline Sparse Tensor Contractions on Vector Processors for Transformer Inference
arXiv:2607. 25504v1 Announce Type: cross Abstract: Fine-grained weight pruning and activation sparsification have emerged as effective approaches for reducing the compute and memory cost of inference for Transformer models.
arXiv AI
Jul 29
Atmospheric Diffusion-Guided Spatio-Temporal Transformer for Nuclear Radiation Forecasting
arXiv:2607. 24774v1 Announce Type: new Abstract: Nuclear radiation, the energy released during atomic decay, poses persistent risks to public health and the environment, and concerns have only grown since the Fukushima accident and the recent commencement of treated-water discharge.
arXiv AI
Jul 29
Representation Capacity-Matched QNN-SNN Twin Construction for Rate-Encoded SNNs
arXiv:2409. 08290v5 Announce Type: replace-cross Abstract: Spiking Neural Networks (SNNs) promise higher energy efficiency over conventional Quantized Artificial Neural Networks (QNNs) due to their event-driven, spike-based computation.
arXiv AI
Jul 29
Pass the Baton: Trajectory-Relayed On-Policy Distillation
arXiv:2607. 26057v1 Announce Type: cross Abstract: On-policy distillation (OPD) grounds token-level supervision in the student's own trajectory, yet suffers from prefix failure: once the student commits to a wrong reasoning direction, all subsequent generation builds on this deviation, producing misdirected continuations that elicit unreliable supervision and waste compute.
arXiv AI
Jul 29
Every Time I Hire a Linguist, Inference Costs Go Down: On Linguistic Rules as Effective Prompt Compressors
arXiv:2607. 25335v1 Announce Type: cross Abstract: Prompt compression shortens LLM input to reduce inference cost, yet existing methods score token importance through LM forward passes.
arXiv AI
Jul 29
CAST: Game Solvers as Turn-Level Teachers for LLM Agents
arXiv:2607. 25308v1 Announce Type: cross Abstract: Training large language models (LLMs) to act in long-horizon games is a promising step toward generalist decision-making, yet reinforcement learning with verifiable rewards (RLVR) relies on sparse final rewards that reveal little about which decisions determine success.
arXiv AI
Jul 29
OrganLens: Organ-Specific Representation Learning for CT Foundation Models
arXiv:2607. 25164v1 Announce Type: cross Abstract: A CT examination captures multiple organs, but many biomedical questions concern abnormalities, prognosis, or longitudinal change in a specific organ.
arXiv AI
Jul 29
Stable FP4 Training via Transposition-Invariant Block Quantization
arXiv:2607. 24953v1 Announce Type: cross Abstract: Reducing training precision is a key lever for improving the e ciency of large language model (LLM) training, but pushing beyond FP8 to 4-bit oating point (FP4) remains challenging due to instability during optimization.
arXiv AI
Jul 29
REPREC: Representation Driven Parameter-Efficient Recommendation System
arXiv:2607. 24845v1 Announce Type: cross Abstract: Large language models (LLMs) have been applied to sequential recommendation by formulating it as a natural language task.
arXiv AI
Jul 29
Speculate While You Reason: Teaching Agents to Predict Their Next Tool Call via Joint Agent-Speculator RL
arXiv:2607. 25816v1 Announce Type: new Abstract: Large language model agents often spend substantial wall-clock time waiting for tool call results.
arXiv AI
Jul 29
OmniDelta: Skill-Driven Budget Allocation for Token Compression in OmniLLMs
arXiv:2607. 25669v1 Announce Type: new Abstract: Emerging Omni-modal Large Language Models (OmniLLMs) enable unified understanding of text, audio, and video, but their long audio-video token sequences introduce substantial memory and inference costs.
arXiv AI
Jul 29
CoTinyVLA: Chain-of-Thought Distillation for a Sub-Billion-Parameter Vision-Language-Action Model
arXiv:2607. 25487v1 Announce Type: new Abstract: Vision-Language-Action (VLA) models translate natural-language commands into robot action sequences, but leading systems on the LIBERO-Plus robustness benchmark use three- to seven-billion-parameter backbones whose memory demands can exceed embedded robotic budgets.
arXiv AI
Jul 29
Salient Knowledge Pathways: Sparse Cross-Modal Routing for Efficient Knowledge-Intensive Multimodal Question Answering
arXiv:2607. 25422v1 Announce Type: new Abstract: Knowledge-intensive multimodal question answering (KI-MMQA) sits at the intersection of three expensive primitives: long visual token sequences, dense retrieval over large external corpora, and full cross-modal fusion.
arXiv AI
Jul 29
SpecPrefetch: Parameter-Efficient Expert Prefetching for Sparse MoE Foundation Models
arXiv:2607. 24787v1 Announce Type: new Abstract: Sparse Mixture-of-Experts (MoE) models expand foundation model capacity through conditional expert activation, but their full expert pools remain difficult to deploy under limited accelerator memory.
arXiv AI
Jul 29
VaLiDRec: Variable-Length LLM-Aligned Semantic IDs for Generative Recommendation
arXiv:2607. 25209v1 Announce Type: cross Abstract: Generative recommendation commonly represents items using fixed-length semantic identifiers (SIDs) constructed through clustering and quantization.
arXiv AI
Jul 29
Are the High-weight Neurons the Important Ones in Image Classification Neural Networks?
arXiv:2607. 25529v1 Announce Type: new Abstract: As neural network models for image classification advance, neurons play critical roles in pruning, backdoor defense, and interpretability.