Good Papers

Showing papers from Dartmouth College Show all papers

70%Highly rated
?Highly ratedVote to see the score
ACL 2025U Notre DameU PennsylvaniaGeorgia Institute of TechnologyDartmouth CollegeMachine unlearning

Modality-Aware Neuron Pruning for Unlearning in Multimodal Large Language Models

Modality-aware neuron pruning removes target knowledge from multimodal LLMs by selectively pruning modality-specific neurons to enable precise unlearning.

Zheyuan Liu, Guangyao Dou, Xiangchi Yuan, Chunhui Zhang and 2 more

Published 2025 · 4 citations

– ReadersNo votes yet
5/20 AI panelreviewers recommend it

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.

AI panel: 5 of 20 reviewers recommend it
lenient 3/5
medium 2/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Dartmouth CollegeDartmouth EngineeringDomain adaptation

Causal Discovery from Unseen Environments

Sophia Xiao, Bijan Mazaheri

Atlanta Poster Session 5, Fri, Dec 11, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

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.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026MIT / Technical University of MuMITMIT Media LabDartmouth CollegeSparse autoencoders

Dual-Contrastive Sparse Autoencoders Reveal Features of Musical Interpretation

Jan Chen, Manuel Cherep, Patricia Maes, Nikhil Singh

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

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.

AI panel: 1 of 20 reviewers recommend it
lenient 1/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Dartmouth CollegeVirginia TechNew YorkMulti-agent LLM systems

Optimize Once, Execute Fast: Latency-Aware Multi-Agent Workflow Learning for Recurrent Queries

Enpei Zhang, Feiyu Qu, Zheng Huang, Dawei Zhou and 2 more

Sydney Poster Session 4, Wed, Dec 9, 5:00 PM–8:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
57%Worth a look
?Worth a lookVote to see the score
NeurIPS 2026Dartmouth CollegeMechanistic interpretability

Knowing Without Saying: How Contextual Evidence Survives but Fails to Surface in Transformers

Ruochen Jin, Tianyu Pang, Chenxi Lin, Lei Hsiung and 4 more

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
1/20 AI panelreviewers recommend it

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.

AI panel: 1 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 1/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026IST AustriaISTALondon School of Economics and PDartmouth CollegeOptimization

Algorithms for Linear Equations with Min and Max Operators Under (Absolutely) Halting Condition

Krishnendu Chatterjee, Ruichen Luo, Raimundo Saona, Jakub Svoboda

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Dartmouth CollegeLLM pretraining & scaling laws

Inside Emergence: Structure-Behaviour Gaps in Language Model Training

Hak Hyun Kim, Yash Raj, Soroush Vosoughi

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Dartmouth CollegeSparse autoencoders

A Curvature Phase Transition Governs Coherence Penalty Efficiency Against Feature Absorption in SAEs

Hak Hyun Kim, Yash Raj, Peter Chin, Soroush Vosoughi

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Dartmouth CollegeCarnegie MellonNew YorkLLM reasoning & chain of thought

When Form Changes but Logic Doesn’t: Building Logic-invariant LLMs through Structures

Xuyuan Liu, Xinshuai Dong, Elynn Chen, Yujun Yan

Atlanta Poster Session 4, Thu, Dec 10, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026Dartmouth CollegeLong-context modeling

The Missing Positional Story in LLMs: A Case Study of Shift-Invariant Attention

Benjamin Huh, Hak Hyun Kim, Yuting Tian, Jason Peng and 2 more

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
45%Niche pick
?Niche pickVote to see the score
NeurIPS 2026PekingDartmouth CollegeU Science and Technology of ChinU TorontoU Southern CaliforniaRL for LLMs

The Heel of RLVR: Benchmark Glory Should Not Outpace Honest Measurement

Shuo Yang, Chiyu Ma, Kexin Huang, Jinda Lu and 10 more

Sydney Poster Session 5, Thu, Dec 10, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
0/20 AI panelreviewers recommend it

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.

AI panel: 0 of 20 reviewers recommend it
lenient 0/5
medium 0/10
strict 0/5
69%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026SpotlightStanfordDartmouth CollegeU California Los AngelesMechanistic interpretability

A Mechanistic Investigation of Theory of Mind in a Large Language Model

Idil K Sahin, Steven M Frankland, Taylor Webb

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026

– ReadersNo votes yet
3/20 AI panelreviewers recommend it

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.

AI panel: 3 of 20 reviewers recommend it
lenient 1/5
medium 2/10
strict 0/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026ColumbiaThe Chinese University of Hong KDartmouth CollegeMicrosoftMicrosoft ResearchLLM agents & planning

Reinforcement World Model Learning for LLM-based Agents

RWML learns action-conditioned world models for LLM agents via self-supervised sim-to-real alignment, outperforming direct task-success RL by up to 6.9 points without expert data.

Xiao Yu, Baolin Peng, Ruize Xu, yelong shen and 5 more

Sydney Poster Session 1, Tue, Dec 8, 10:00 AM–1:00 PM, Hall 1-4 · Published 2026 · ▲ 28 on Hugging Face

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

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.

AI panel: 10 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 0/5
78%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Dartmouth CollegeVideo generation

AtlasVid: Efficient Ultra-High-Resolution Long Video Generation via Decoupled Global-Local Modeling

AtlasVid decouples global-local video diffusion modeling to generate 4K long videos with 60.9x speedup via low-resolution proxies and hierarchical attention, training only at 720P.

Ziyang Mai, Yuyao Zhang, Yu-Wing Tai

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
11/20 AI panelreviewers recommend it

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.

AI panel: 11 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 1/5
86%Must read
?Must readVote to see the score
NeurIPS 2026Department of Computer Science aU California, BerkeleyDartmouth CollegeUC BerkeleyAutomated scientific discovery

Learning to Discover Iterative Spectral Algorithms

AutoSpec is a neural framework that discovers iterative spectral algorithms via self-supervised prediction of recurrence coefficients, yielding order-of-magnitude speedups over classical baselines.

Zihang Liu, Oleg Balabanov, Yaoqing Yang, Michael Mahoney

Paris Poster Session 6, Fri, Dec 11, 2:30 PM–4:30 PM, Paris Poster Hall · Published 2026

– ReadersNo votes yet
14/20 AI panelreviewers recommend it

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.

AI panel: 14 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 2/5
72%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Dartmouth College3D vision & reconstruction

Perceive-then-Plan: Layout-as-Policy for Monocular 3D Scene Layout Estimation

Perceive-then-plan framework LaP treats 3D layout estimation as iterative policy refinement via discrete actions, yielding more physically coherent scenes from single images.

Junwei Zhou, Yu-Wing Tai

Atlanta Poster Session 1, Wed, Dec 9, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
8/20 AI panelreviewers recommend it

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.

AI panel: 8 of 20 reviewers recommend it
lenient 5/5
medium 3/10
strict 0/5
89%Must read
?Must readVote to see the score
NeurIPS 2026BenchFlowOhio State University, ColumbusAmazonDartmouth CollegeU California, DavisAgent benchmarks & environments

SkillsBench: Benchmarking How Well Agent Skills Work Across Diverse Tasks

SkillsBench benchmarks agent skills across 87 tasks, finding curated skills boost pass rates by 16.6 points, with focused small bundles often outperforming larger ones.

Xiangyi Li, Yimin Liu, Wenbo Chen, Shenghan Zheng and 36 more

Atlanta Poster Session 3, Thu, Dec 10, 10:00 AM–1:00 PM, Hall C1 · Published 2026

– ReadersNo votes yet
16/20 AI panelreviewers recommend it

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.

AI panel: 16 of 20 reviewers recommend it
lenient 5/5
medium 7/10
strict 4/5
76%Highly rated
?Highly ratedVote to see the score
NeurIPS 2026Dartmouth CollegeDiffusion models

When Latents Forget Pixels: Restoring Fidelity in Diffusion Transformer Super-Resolution

PGSR preserves pre-VAE pixel evidence from upscaled low-resolution images to guide diffusion-transformer super-resolution, improving fidelity and the realism-fidelity trade-off.

Yu Shi, Yuyao Zhang, Yu-Wing Tai

Atlanta Poster Session 6, Fri, Dec 11, 4:30 PM–7:30 PM, Hall C1 · Published 2026

– ReadersNo votes yet
10/20 AI panelreviewers recommend it

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.

AI panel: 10 of 20 reviewers recommend it
lenient 4/5
medium 6/10
strict 0/5
86%Must read
?Must readVote to see the score
NeurIPS 2026Virginia Polytechnic Institute aU Wisconsin MadisonDartmouth CollegeVirginia TechLLM reasoning & chain of thought

SAGE: Mitigating Long-Horizon Reasoning Biases via Topological Guidance

SAGE mitigates long-horizon reasoning biases via symbolic closure analysis, using algebraic sparsification and hyperbolic guidance to suppress spurious branching and compounding errors, achieving up to 8-fold gains on sparse-reward benchmarks.

Xinyue Zeng, Jiawei zhang, Yujun Yan, Dawei Zhou

Atlanta Poster Session 2, Wed, Dec 9, 4:30 PM–7:30 PM, Hall C1 · Published 2026 · ▲ 8 on Hugging Face · Code

– ReadersNo votes yet
14/20 AI panelreviewers recommend it

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.

AI panel: 14 of 20 reviewers recommend it
lenient 3/5
medium 9/10
strict 2/5