Souvik Kundu
~Souvik_Kundu2
16
论文总数
8.0
年均投稿
平均评分
接收情况9/16
会议分布
ICLR
11
NeurIPS
2
COLM
2
ICML
1
发表论文 (16 篇)
202511 篇
4
MambaExtend: A Training-Free Approach to Improve Long Context Extension of Mamba
ICLR 2025Poster
3
Top-H Decoding: Adapting the Creativity and Coherence with Bounded Entropy in Text Generation
NeurIPS 2025Poster
4
On-the-Fly Adaptive Distillation of Transformer to Dual-State Linear Attention for Long-Context LLM Serving
ICML 2025Poster
4
Scaling Long Context Training Data by Long-Distance Referrals
ICLR 2025Poster
3
VERT: A SystemVerilog Assertion Dataset to Improve Hardware Verification with LLMs
ICLR 2025Rejected
4
CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing
COLM 2025Poster
4
SEAL: Steerable Reasoning Calibration of Large Language Models for Free
COLM 2025Poster
4
CITER: Collaborative Inference for Efficient Large Language Model Decoding with Token-Level Routing
ICLR 2025Rejected
4
LANTERN: Accelerating Visual Autoregressive Models with Relaxed Speculative Decoding
ICLR 2025Poster
4
MeZO-A$^{3}$dam: Memory-efficient Zeroth-order Adam with Adaptivity Adjustments for Fine-tuning LLMs
ICLR 2025withdrawn
5
ShareLoRA: Less Tuning, More Performance for LoRA Fine-tuning of LLMs
ICLR 2025withdrawn
20245 篇
3
Junk DNA Hypothesis: A Task-Centric Angle of LLM Pre-trained Weights through Sparsity
ICLR 2024Rejected
3
DIA: Diffusion based Inverse Network Attack on Collaborative Inference
ICLR 2024withdrawn
4
Fusing Models with Complementary Expertise
ICLR 2024Poster
4
Finding Adversarially Robust Graph Lottery Tickets
ICLR 2024Rejected
3
ShiftAddLLM: Accelerating Pretrained LLMs via Post-Training Multiplication-Less Reparameterization
NeurIPS 2024Poster