Search papers, labs, and topics across Lattice.
Affiliation:, Shanghai Jiao Tong University
12
7
12
20
Skill2Query transforms agent skill retrieval by generating contextually grounded pseudo-queries that boost retrieval accuracy and agent performance.
VAD reveals that isolating visual evidence can dramatically improve target reconstruction in multimodal learning, leading to more accurate student outputs.
GraphBU achieves a remarkable 96.7% feasibility rate while preserving structural integrity, revolutionizing how MILP instances are generated for solver development.
Coordinated evidence acquisition in multi-hop RAG can boost performance by nearly 6 F1 points, revealing the critical role of learned control in retrieval processes.
DiffCold shatters the seesaw dilemma in item recommendation, enabling accurate cold-start predictions without sacrificing the performance of warm items.
Skill organization can dramatically enhance agent performance, with a 4.1% increase in successful outcomes when using Progressive Disclosure over traditional methods.
N眉shu-PitchVITS not only revives an endangered script but also sets a new benchmark in low-resource TTS systems by achieving superior speech synthesis quality through innovative pitch conditioning.
LatentSkill achieves a 21.4-point increase in task success while slashing prefill token usage by over 64%, revolutionizing how LLM agents utilize skills.
LLMs' final layers might be holding your recommendation system back: representations from middle layers actually perform *better*, and a modular compression approach can unlock significant gains.
LMM-based GUI agents stick out like a sore thumb in human-centric mobile environments, but simple techniques can make them blend in without sacrificing utility.
Function calling gets a serious upgrade: a new reward model and inference scaling technique boosts performance by focusing on the *process* of tool use, not just the outcome.
Current LLM evaluation benchmarks often conflate chatbots and true AI agents, leading to misaligned research efforts, but this survey provides a framework for targeted evaluation based on environmental complexity and agent capabilities.
