相关论文: ZEBRA: Zero-shot Budgeted Resource Allocation for …

Current Large Language Models (LLMs) have shown strong reasoning capabilities in commonsense question answering benchmarks, but the process underlying their success remains largely opaque. As a consequence, recent approaches have equipped…

Large language models (LLMs) exhibit substantial potential across diverse scientific disciplines, including materials science. A property prediction framework, ZEBRA-Prop (Zero-Shot Embedding-Based Rapid and Accessible Regression Model for…

Recent efforts in LLM alignment have focused on constructing large-scale preference datasets via human or Artificial Intelligence (AI) annotators. However, such approaches rely on instance-wise supervision, incurring substantial annotation…

Test-time scaling has become a dominant paradigm for improving LLM agent reliability, yet current approaches treat compute as an abundant resource, allowing agents to exhaust token and tool budgets on redundant steps or dead-end…

Building on advancements in Large Language Models (LLMs), we can tackle complex analytical and mathematical reasoning tasks requiring nuanced contextual understanding. A prime example of such complex tasks is modelling resource allocation…

Zero-shot reasoning methods with Large Language Models (LLMs) offer significant advantages including great generalization to novel tasks and reduced dependency on human-crafted examples. However, the current zero-shot methods still have…

Existing LLM routing frameworks treat queries as independent events, neglecting the sequential nature of real-world user sessions constrained by global computational budgets. This mismatch inevitably leads to budget bankruptcy: myopic…

With the growing demand for deploying large language models (LLMs) across diverse applications, improving their inference efficiency is crucial for sustainable and democratized access. However, retraining LLMs to meet new user-specific…

Large Language Models (LLMs) can self-improve through reinforcement learning, where they generate trajectories to explore and discover better solutions. However, this exploration process is computationally expensive, often forcing current…

This paper presents an empirical study of a multi-model zero-shot pipeline for knowledge graph construction and exploitation, executed entirely through local inference on consumer-grade hardware. We propose a reproducible evaluation…

This paper introduces a novel approach to enhance the capabilities of Large Language Models (LLMs) in processing and understanding extensive text sequences, a critical aspect in applications requiring deep comprehension and synthesis of…

The proliferation of camera-enabled devices and large video repositories has led to a diverse set of video analytics applications. These applications rely on video pipelines, represented as DAGs of operations, to transform videos, process…

LLM search agents increasingly rely on tools at inference time, but their trajectories are often constrained by hard limits on both tool calls and generated tokens. Under such dual budgets, better answers require not only stronger models,…

Training large language models (LLMs) encounters challenges in GPU memory consumption due to the high memory requirements of model states. The widely used Zero Redundancy Optimizer (ZeRO) addresses this issue through strategic sharding but…

Optimizing the advertiser's cumulative value of winning impressions under budget constraints poses a complex challenge in online advertising, under the paradigm of AI-Generated Bidding (AIGB). Advertisers often have personalized objectives…

Evaluating and predicting the performance of large language models (LLMs) in multi-turn conversational settings is critical yet computationally expensive; key events -- e.g., jailbreaks or successful task completion by an agent -- often…

Running Large Language Models (LLMs) on edge devices is constrained by high compute and memory demands posing a barrier for real-time applications in sectors like healthcare, education, and embedded systems. Current solutions such as…

Recently, large reasoning models demonstrate exceptional performance on various tasks. However, reasoning models always consume excessive tokens even for simple queries, leading to resource waste and prolonged user latency. To address this…

As the capabilities of Vision-Language Models (VLMs) advance, they can process increasingly large inputs, which, unlike in LLMs, generates significant visual token redundancy and leads to prohibitive inference costs. While many methods aim…

Production LLM deployments increasingly maintain heterogeneous model pools spanning order-of-magnitude cost differences. Existing routers make binary strong-vs-weak decisions and couple learned parameters to specific model identities,…