activity
20242026
collaborators
Showing cs.CLShow all

7 papers · 1 filter

cs.CL2026

Learning When to Attend: Conditional Memory Access for Long-Context LLMs

Sakshi Choudhary, Aditya Chattopadhyay, Luca Zancato +4

Language models struggle to generalize beyond pretraining context lengths, limiting long-horizon reasoning and retrieval. Continued pretraining on long-context data can help but is…

cs.CL2026

DLLG: Dynamic Logit-Level Gating of LLM Experts

Bingnan Li, Zhaoyang Zhang, Xiaoze Liu +6

Leveraging multiple specialized LLMs can combine complementary strengths, but existing approaches trade adaptability for stability: routing commits prematurely, heuristic ensemblin…

cs.CL2026

Asymmetric Actor-Critic for Multi-turn LLM Agents

Shuli Jiang, Zhaoyang Zhang, Yi Zhang +3

Large language models (LLMs) exhibit strong reasoning and conversational abilities, but ensuring reliable behavior in multi-turn interactions remains challenging. In many real-worl…

cs.CL2025

Learning to Focus: Focal Attention for Selective and Scalable Transformers

Dhananjay Ram, Wei Xia, Stefano Soatto

Attention is a core component of transformer architecture, whether encoder-only, decoder-only, or encoder-decoder model. However, the standard softmax attention often produces nois…

cs.CL2025

Maximally-Informative Retrieval for State Space Model Generation

Evan Becker, Benjamin Bowman, Matthew Trager +4

Given a query and dataset, the optimal way of answering the query is to make use all the information available. Modern LLMs exhibit impressive ability to memorize training data, bu…

cs.CL2025

Expansion Span: Combining Fading Memory and Retrieval in Hybrid State Space Models

Elvis Nunez, Luca Zancato, Benjamin Bowman +3

The "state" of State Space Models (SSMs) represents their memory, which fades exponentially over an unbounded span. By contrast, Attention-based models have "eidetic" (i.e., verbat…