Picture for Saravan Rajmohan

Saravan Rajmohan

Reason-before-Retrieve: One-Stage Reflective Chain-of-Thoughts for Training-Free Zero-Shot Composed Image Retrieval

Add code
Dec 15, 2024
Viaarxiv icon

Large Action Models: From Inception to Implementation

Add code
Dec 13, 2024
Viaarxiv icon

TURBOATTENTION: Efficient Attention Approximation For High Throughputs LLMs

Add code
Dec 11, 2024
Viaarxiv icon

SWEPO: Simultaneous Weighted Preference Optimization for Group Contrastive Alignment

Add code
Dec 05, 2024
Viaarxiv icon

Large Language Model-Brained GUI Agents: A Survey

Add code
Dec 03, 2024
Figure 1 for Large Language Model-Brained GUI Agents: A Survey
Figure 2 for Large Language Model-Brained GUI Agents: A Survey
Figure 3 for Large Language Model-Brained GUI Agents: A Survey
Figure 4 for Large Language Model-Brained GUI Agents: A Survey
Viaarxiv icon

Ensuring Fair LLM Serving Amid Diverse Applications

Add code
Nov 24, 2024
Figure 1 for Ensuring Fair LLM Serving Amid Diverse Applications
Figure 2 for Ensuring Fair LLM Serving Amid Diverse Applications
Figure 3 for Ensuring Fair LLM Serving Amid Diverse Applications
Figure 4 for Ensuring Fair LLM Serving Amid Diverse Applications
Viaarxiv icon

Sharingan: Extract User Action Sequence from Desktop Recordings

Add code
Nov 13, 2024
Viaarxiv icon

RuAG: Learned-rule-augmented Generation for Large Language Models

Add code
Nov 04, 2024
Figure 1 for RuAG: Learned-rule-augmented Generation for Large Language Models
Figure 2 for RuAG: Learned-rule-augmented Generation for Large Language Models
Figure 3 for RuAG: Learned-rule-augmented Generation for Large Language Models
Figure 4 for RuAG: Learned-rule-augmented Generation for Large Language Models
Viaarxiv icon

Token-level Proximal Policy Optimization for Query Generation

Add code
Nov 01, 2024
Viaarxiv icon

Self-Evolved Reward Learning for LLMs

Add code
Nov 01, 2024
Figure 1 for Self-Evolved Reward Learning for LLMs
Figure 2 for Self-Evolved Reward Learning for LLMs
Figure 3 for Self-Evolved Reward Learning for LLMs
Figure 4 for Self-Evolved Reward Learning for LLMs
Viaarxiv icon