Showing papers from University of Georgia Show all papers
Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
ROMA improves multimodal reasoning robustness to visual corruption via dual-pass RL optimization that avoids reward poisoning while preserving clean accuracy.
Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 5 on Hugging Face
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
DeepArrhythmia classifies ECG arrhythmias via segment context and selective evidence routing, improving beat-level predictions with explicit physiological grounding.
Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
MedVIGIL evaluates medical vision-language models under broken visual evidence via clinician-supervised probes, revealing a 14.1-point gap between top models and radiologist reliability.
Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
PoLAR-VBLL uses orthogonalized low-rank adapters with Bayesian last-layer inference to fine-tune LLMs with scalable, well-calibrated uncertainty quantification.
Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
PLATO uses a pointer-network actor and GNN critic to handle open multi-agent reinforcement learning with unbounded agent and task spaces, achieving strong zero-shot generalization.
Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
StraTA introduces trajectory-level strategies into agentic reinforcement learning via hierarchical rollout training, improving long-horizon decision-making and reaching 93.1% on ALFWorld.
Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
LCDD constructs sparse, causally necessary subnetworks for SFT behaviors, and SFT-Eraser reverses them via activation-matched soft prompts without weight changes.
Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
GazeWorld models radiologist eye-tracking as fixation trajectories through images to pretrain medical representations that achieve state-of-the-art diagnostic and gaze prediction accuracy without requiring real gaze data at inference.
Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
Palette enables modular, efficient relaxation of LLM refusal behaviors for authorized domains via lightweight adaptation and parameter merging while preserving general safety.
Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.
ActQuant uses action-guided mixed-precision quantization to compress vision-language-action models below 4 bits, retaining 95% task performance at 3 bpw and enabling edge deployment via native C/C++ kernels.
Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026 · ▲ 2 on Hugging Face · Code ★ 19
Readers and the AI panel: vote on this paper to see what they said.
Only vote on papers you've read. Sign in with GitHub to vote.