· ai
[Paper] LLMs can Compress LLMs: Adaptive Pruning by Agents
As Large Language Models (LLMs) continue to scale, post-training pruning has emerged as a promising approach to reduce computational costs while preserving perf...
-
- · ai
[Paper] Contrastive Geometric Learning Unlocks Unified Structure- and Ligand-Based Drug Design
Structure-based and ligand-based computational drug design have traditionally relied on disjoint data sources and modeling assumptions, limiting their joint use...
- · ai
[Paper] Routing with Generated Data: Annotation-Free LLM Skill Estimation and Expert Selection
Large Language Model (LLM) routers dynamically select optimal models for given inputs. Existing approaches typically assume access to ground-truth labeled data,...
- · ai
[Paper] DeepResearchEval: An Automated Framework for Deep Research Task Construction and Agentic Evaluation
Deep research systems are widely used for multi-step web research, analysis, and cross-source synthesis, yet their evaluation remains challenging. Existing benc...
- · ai
[Paper] Disentangling Task Conflicts in Multi-Task LoRA via Orthogonal Gradient Projection
Multi-Task Learning (MTL) combined with Low-Rank Adaptation (LoRA) has emerged as a promising direction for parameter-efficient deployment of Large Language Mod...
- · ai
[Paper] Automating Supply Chain Disruption Monitoring via an Agentic AI Approach
Modern supply chains are increasingly exposed to disruptions from geopolitical events, demand shocks, trade restrictions, to natural disasters. While many of th...
- · ai
[Paper] STEP3-VL-10B Technical Report
We present STEP3-VL-10B, a lightweight open-source foundation model designed to redefine the trade-off between compact efficiency and frontier-level multimodal ...
- · ai
[Paper] Collaborative Multi-Agent Test-Time Reinforcement Learning for Reasoning
Multi-agent systems have evolved into practical LLM-driven collaborators for many applications, gaining robustness from diversity and cross-checking. However, m...
- · ai
[Paper] SCE-SLAM: Scale-Consistent Monocular SLAM via Scene Coordinate Embeddings
Monocular visual SLAM enables 3D reconstruction from internet video and autonomous navigation on resource-constrained platforms, yet suffers from scale drift, i...
- · ai
[Paper] Self-Supervised Animal Identification for Long Videos
Identifying individual animals in long-duration videos is essential for behavioral ecology, wildlife monitoring, and livestock management. Traditional methods r...
- · ai
[Paper] LiteEmbed: Adapting CLIP to Rare Classes
Large-scale vision-language models such as CLIP achieve strong zero-shot recognition but struggle with classes that are rarely seen during pretraining, includin...
- · ai
[Paper] Image2Garment: Simulation-ready Garment Generation from a Single Image
Estimating physically accurate, simulation-ready garments from a single image is challenging due to the absence of image-to-physics datasets and the ill-posed n...