14 papers
TreeHCA: Hindsight-Guided Exploration and Credit Assignment for Multi-Turn LLM Agents
Debajoy Mukherjee, Jeremy Carleton, Sushil Vemuri +2
Outcome-supervised group-relative policy optimization (GRPO) assigns the same advantage to every token in an LLM agent trajectory, leaving useful and unhelpful decisions undifferen…
EDATracer: An Agentic Framework for Large-Scale EDA Artifact Analysis
Phat Tieu, Sayanti Jana, Matthew DeLorenzo +5
Modern chip design relies on electronic design automation (EDA) tools that generate large, heterogeneous artifacts, including source files, scripts, logs, netlists, and reports. An…
EvoPlan: Evolutionary Neuro-Symbolic Robot Planning with Spatio-Temporal Guarantees
Bhavya Sai Nukapotula, Samin Moosavi, Haoze Wang +4
LLM-based robot planners are fluent but cannot guarantee that their plans are executable or safe. Classical PDDL planners can guarantee these properties, but only after the problem…
DarkVGGT: Seeing Through Darkness Using Thermal Geometry
Minseong Kweon, Wenyuan Zhao, Nuo Chen +6
Recent feed-forward 3D reconstruction methods have demonstrated strong performance and flexibility in efficient end-to-end scene geometry estimation from image streams. However, th…
EgoTL: Egocentric Think-Aloud Chains for Long-Horizon Tasks
Lulin Liu, Dayou Li, Yiqing Liang +8
Large foundation models have made significant advances in embodied intelligence, enabling synthesis and reasoning over egocentric input for household tasks. However, VLM-based auto…
Tiny-Twin: A CPU-Native Full-stack Digital Twin for NextG Cellular Networks
Ali Mamaghani, Ushasi Ghosh, Srinivas Shakkottai +2
Modern wireless applications demand testing environments that capture the full complexity of next-generation (NextG) cellular networks. While digital twins promise realistic emulat…
GSpaRC: Gaussian Splatting for Real-time Reconstruction of RF Channels
Bhavya Sai Nukapotula, Rishabh Tripathi, Seth Pregler +3
Channel state information (CSI) is essential for adaptive beamforming and maintaining robust links in wireless communication systems. However, acquiring CSI incurs significant over…
MAVIS: Multi-Objective Alignment via Inference-Time Value-Guided Selection
Jeremy Carleton, Debajoy Mukherjee, Srinivas Shakkottai +1
Large Language Models (LLMs) are increasingly deployed across diverse applications that demand balancing multiple, often conflicting, objectives -- such as helpfulness, harmlessnes…
PITA: Preference-Guided Inference-Time Alignment for LLM Post-Training
Sarat Chandra Bobbili, Ujwal Dinesha, Dheeraj Narasimha +1
Inference-time alignment enables large language models (LLMs) to generate outputs aligned with end-user preferences without further training. Recent post-training methods achieve t…
Risk-Averse Finetuning of Large Language Models
Sapana Chaudhary, Ujwal Dinesha, Dileep Kalathil +1
We consider the challenge of mitigating the generation of negative or toxic content by the Large Language Models (LLMs) in response to certain prompts. We propose integrating risk-…
DOPL: Direct Online Preference Learning for Restless Bandits with Preference Feedback
Guojun Xiong, Ujwal Dinesha, Debajoy Mukherjee +2
Restless multi-armed bandits (RMAB) has been widely used to model constrained sequential decision making problems, where the state of each restless arm evolves according to a Marko…
Multi-Provider Resource Scheduling in Massive MIMO Radio Access Networks
Qing An, Divyanshu Pandey, Rahman Doost-Mohammady +2
An important aspect of 5G networks is the development of Radio Access Network (RAN) slicing, a concept wherein the virtualized infrastructure of wireless networks is subdivided int…
CONGO: Compressive Online Gradient Optimization
Jeremy Carleton, Prathik Vijaykumar, Divyanshu Saxena +3
We address the challenge of zeroth-order online convex optimization where the objective function's gradient exhibits sparsity, indicating that only a small number of dimensions pos…
Windex: Index-Driven Contextual Scheduler for Scalable Service Guarantees in NextG Cellular Networks
Archana Bura, Ushasi Ghosh, Dinesh Bharadia +2
Next-generation cellular networks must support heterogeneous service objectives, ranging from throughput-oriented eMBB to latency- and regularity-constrained URLLC and XR traffic.…